In this paper,we propose hierarchical attention dual network(DNet)for fine-grained image classification.The DNet can randomly select pairs of inputs from the dataset and compare the differences between them through hi...In this paper,we propose hierarchical attention dual network(DNet)for fine-grained image classification.The DNet can randomly select pairs of inputs from the dataset and compare the differences between them through hierarchical attention feature learning,which are used simultaneously to remove noise and retain salient features.In the loss function,it considers the losses of difference in paired images according to the intra-variance and inter-variance.In addition,we also collect the disaster scene dataset from remote sensing images and apply the proposed method to disaster scene classification,which contains complex scenes and multiple types of disasters.Compared to other methods,experimental results show that the DNet with hierarchical attention is robust to different datasets and performs better.展开更多
Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scal...Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scales.A cul-tural heritage image is one of thefine-grained images because each image has the same similarity in most cases.Using the classification technique,distinguishing cultural heritage architecture may be difficult.This study proposes a cultural heri-tage content retrieval method using adaptive deep learning forfine-grained image retrieval.The key contribution of this research was the creation of a retrieval mod-el that could handle incremental streams of new categories while maintaining its past performance in old categories and not losing the old categorization of a cul-tural heritage image.The goal of the proposed method is to perform a retrieval task for classes.Incremental learning for new classes was conducted to reduce the re-training process.In this step,the original class is not necessary for re-train-ing which we call an adaptive deep learning technique.Cultural heritage in the case of Thai archaeological site architecture was retrieved through machine learn-ing and image processing.We analyze the experimental results of incremental learning forfine-grained images with images of Thai archaeological site architec-ture from world heritage provinces in Thailand,which have a similar architecture.Using afine-grained image retrieval technique for this group of cultural heritage images in a database can solve the problem of a high degree of similarity among categories and a high degree of dissimilarity for a specific category.The proposed method for retrieving the correct image from a database can deliver an average accuracy of 85 percent.Adaptive deep learning forfine-grained image retrieval was used to retrieve cultural heritage content,and it outperformed state-of-the-art methods infine-grained image retrieval.展开更多
Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fin...Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.展开更多
Fine-grained Image Recognition(FGIR)task is dedicated to distinguishing similar sub-categories that belong to the same super-category,such as bird species and car types.In order to highlight visual differences,existin...Fine-grained Image Recognition(FGIR)task is dedicated to distinguishing similar sub-categories that belong to the same super-category,such as bird species and car types.In order to highlight visual differences,existing FGIR works often follow two steps:discriminative sub-region localization and local feature representation.However,these works pay less attention on global context information.They neglect a fact that the subtle visual difference in challenging scenarios can be highlighted through exploiting the spatial relationship among different subregions from a global view point.Therefore,in this paper,we consider both global and local information for FGIR,and propose a collaborative teacher-student strategy to reinforce and unity the two types of information.Our framework is implemented mainly by convolutional neural network,referred to Teacher-Student Based Attention Convolutional Neural Network(T-S-ACNN).For fine-grained local information,we choose the classic Multi-Attention Network(MA-Net)as our baseline,and propose a type of boundary constraint to further reduce background noises in the local attention maps.In this way,the discriminative sub-regions tend to appear in the area occupied by fine-grained objects,leading to more accurate sub-region localization.For fine-grained global information,we design a graph convolution based Global Attention Network(GA-Net),which can combine extracted local attention maps from MA-Net with non-local techniques to explore spatial relationship among subregions.At last,we develop a collaborative teacher-student strategy to adaptively determine the attended roles and optimization modes,so as to enhance the cooperative reinforcement of MA-Net and GA-Net.Extensive experiments on CUB-200-2011,Stanford Cars and FGVC Aircraft datasets illustrate the promising performance of our framework.展开更多
Low-resolution(LR)fine-grained image recognition requires the ability to recognize the subcategories of LR samples with limited fine-grained details.The existing methods do not make full use of the guiding and constra...Low-resolution(LR)fine-grained image recognition requires the ability to recognize the subcategories of LR samples with limited fine-grained details.The existing methods do not make full use of the guiding and constraining capabilities of category-related knowledge to recover and extract the fine-grained features of LR data;thus these methods have a limited ability to learn the global and local fine-grained features of LR data.In this paper,we propose an enhanced feature representation network(EFR-Net)based on categorical knowledge guidance to capture delicate and reliable fine-grained feature descriptions of LR data and improve the recognition accuracy.First,to overcome the challenges posed by the limited fine-grained details in LR data,we design a classwise distillation loss.This loss function transfers the high-quality features of class-specific high-resolution(HR)samples into the feature learning of the same-category LR samples by using a memory bank.In this way,the global representation of LR images is closer to the meaningful and high-quality image features.Second,considering that fine-grained discriminative features are often hidden in object parts,we present a group of part queries to learn the positional information where the discriminative cues exist across all categories,and we then use the queries to decode diverse and discriminative part features.The global representation,in combination with the local discriminative features,creates more comprehensive and meaningful feature descriptions of the LR fine-grained objects,thus improving the recognition performance.Extensive comparison experiments on four LR datasets demonstrate the effectiveness of EFR-Net.展开更多
Finding more specific subcategories within a larger category is the goal of fine-grained image classification(FGIC),and the key is to find local discriminative regions of visual features.Most existing methods use trad...Finding more specific subcategories within a larger category is the goal of fine-grained image classification(FGIC),and the key is to find local discriminative regions of visual features.Most existing methods use traditional convolutional operations to achieve fine-grained image classification.However,traditional convolution cannot extract multi-scale features of an image and existing methods are susceptible to interference from image background information.Therefore,to address the above problems,this paper proposes an FGIC model(Attention-PCNN)based on hybrid attention mechanism and pyramidal convolution.The model feeds the multi-scale features extracted by the pyramidal convolutional neural network into two branches capturing global and local information respectively.In particular,a hybrid attention mechanism is added to the branch capturing global information in order to reduce the interference of image background information and make the model pay more attention to the target region with fine-grained features.In addition,the mutual-channel loss(MC-LOSS)is introduced in the local information branch to capture fine-grained features.We evaluated the model on three publicly available datasets CUB-200-2011,Stanford Cars,FGVCAircraft,etc.Compared to the state-of-the-art methods,the results show that Attention-PCNN performs better.展开更多
Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications.However,existing approaches often rely on manually zooming remote sensing images at diff...Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications.However,existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples.This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios.To address this limitation,we introduce the million-scale fine-grained geospatial scene classification dataset(MEET),which contains over 1.03 million zoom-free remote sensing scene samples,manually annotated into 80 fine-grained categories.In MEET,each scene sample follows a scene-in-scene layout,where the central scene serves as the reference,and auxiliary scenes provide crucial spatial context for fine-grained classification.Moreover,to tackle the emerging challenge of scene-in-scene classification,we present the context-aware transformer(CAT),a model specifically designed for this task,which adaptively fuses spatial context to accurately classify the scene samples.CAT adaptively fuses spatial context to accurately classify the scene samples by learning attentional features that capture the relationships between the center and auxiliary scenes.Based on MEET,we establish a comprehensive benchmark for fine-grained geospatial scene classification,evaluating CAT against 11 competitive baselines.The results demonstrate that CAT significantly outperforms these baselines,achieving a 1.88%higher balanced accuracy(BA)with the Swin-Large backbone,and a notable 7.87%improvement with the Swin-Huge backbone.Further experiments validate the effectiveness of each module in CAT and show the practical applicability of CAT in the urban functional zone mapping.The source code and dataset will be publicly available at https://jerrywyn.github.io/project/MEET.html.展开更多
Joint Multimodal Aspect-based Sentiment Analysis(JMASA)is a significant task in the research of multimodal fine-grained sentiment analysis,which combines two subtasks:Multimodal Aspect Term Extraction(MATE)and Multimo...Joint Multimodal Aspect-based Sentiment Analysis(JMASA)is a significant task in the research of multimodal fine-grained sentiment analysis,which combines two subtasks:Multimodal Aspect Term Extraction(MATE)and Multimodal Aspect-oriented Sentiment Classification(MASC).Currently,most existing models for JMASA only perform text and image feature encoding from a basic level,but often neglect the in-depth analysis of unimodal intrinsic features,which may lead to the low accuracy of aspect term extraction and the poor ability of sentiment prediction due to the insufficient learning of intra-modal features.Given this problem,we propose a Text-Image Feature Fine-grained Learning(TIFFL)model for JMASA.First,we construct an enhanced adjacency matrix of word dependencies and adopt graph convolutional network to learn the syntactic structure features for text,which addresses the context interference problem of identifying different aspect terms.Then,the adjective-noun pairs extracted from image are introduced to enable the semantic representation of visual features more intuitive,which addresses the ambiguous semantic extraction problem during image feature learning.Thereby,the model performance of aspect term extraction and sentiment polarity prediction can be further optimized and enhanced.Experiments on two Twitter benchmark datasets demonstrate that TIFFL achieves competitive results for JMASA,MATE and MASC,thus validating the effectiveness of our proposed methods.展开更多
Digital watermarking technology plays an important role in detecting malicious tampering and protecting image copyright.However,in practical applications,this technology faces various problems such as severe image dis...Digital watermarking technology plays an important role in detecting malicious tampering and protecting image copyright.However,in practical applications,this technology faces various problems such as severe image distortion,inaccurate localization of the tampered regions,and difficulty in recovering content.Given these shortcomings,a fragile image watermarking algorithm for tampering blind-detection and content self-recovery is proposed.The multi-feature watermarking authentication code(AC)is constructed using texture feature of local binary patterns(LBP),direct coefficient of discrete cosine transform(DCT)and contrast feature of gray level co-occurrence matrix(GLCM)for detecting the tampered region,and the recovery code(RC)is designed according to the average grayscale value of pixels in image blocks for recovering the tampered content.Optimal pixel adjustment process(OPAP)and least significant bit(LSB)algorithms are used to embed the recovery code and authentication code into the image in a staggered manner.When detecting the integrity of the image,the authentication code comparison method and threshold judgment method are used to perform two rounds of tampering detection on the image and blindly recover the tampered content.Experimental results show that this algorithm has good transparency,strong and blind detection,and self-recovery performance against four types of malicious attacks and some conventional signal processing operations.When resisting copy-paste,text addition,cropping and vector quantization under the tampering rate(TR)10%,the average tampering detection rate is up to 94.09%,and the peak signal-to-noise ratio(PSNR)of the watermarked image and the recovered image are both greater than 41.47 and 40.31 dB,which demonstrates its excellent advantages compared with other related algorithms in recent years.展开更多
A large-scale view of the magnetospheric cusp is expected to be obtained by the Soft X-ray Imager(SXI)onboard the Solar wind Magnetosphere Ionosphere Link Explorer(SMILE).However,it is challenging to trace the three-d...A large-scale view of the magnetospheric cusp is expected to be obtained by the Soft X-ray Imager(SXI)onboard the Solar wind Magnetosphere Ionosphere Link Explorer(SMILE).However,it is challenging to trace the three-dimensional cusp boundary from a two-dimensional X-ray image because the detected X-ray signals will be integrated along the line of sight.In this work,a global magnetohydrodynamic code was used to simulate the X-ray images and photon count images,assuming an interplanetary magnetic field with a pure Bz component.The assumption of an elliptic cusp boundary at a given altitude was used to trace the equatorward and poleward boundaries of the cusp from a simulated X-ray image.The average discrepancy was less than 0.1 RE.To reduce the influence of instrument effects and cosmic X-ray backgrounds,image denoising was considered before applying the method above to SXI photon count images.The cusp boundaries were reasonably reconstructed from the noisy X-ray image.展开更多
Images taken in dim environments frequently exhibit issues like insufficient brightness,noise,color shifts,and loss of detail.These problems pose significant challenges to dark image enhancement tasks.Current approach...Images taken in dim environments frequently exhibit issues like insufficient brightness,noise,color shifts,and loss of detail.These problems pose significant challenges to dark image enhancement tasks.Current approaches,while effective in global illumination modeling,often struggle to simultaneously suppress noise and preserve structural details,especially under heterogeneous lighting.Furthermore,misalignment between luminance and color channels introduces additional challenges to accurate enhancement.In response to the aforementioned difficulties,we introduce a single-stage framework,M2ATNet,using the multi-scale multi-attention and Transformer architecture.First,to address the problems of texture blurring and residual noise,we design a multi-scale multi-attention denoising module(MMAD),which is applied separately to the luminance and color channels to enhance the structural and texture modeling capabilities.Secondly,to solve the non-alignment problem of the luminance and color channels,we introduce the multi-channel feature fusion Transformer(CFFT)module,which effectively recovers the dark details and corrects the color shifts through cross-channel alignment and deep feature interaction.To guide the model to learn more stably and efficiently,we also fuse multiple types of loss functions to form a hybrid loss term.We extensively evaluate the proposed method on various standard datasets,including LOL-v1,LOL-v2,DICM,LIME,and NPE.Evaluation in terms of numerical metrics and visual quality demonstrate that M2ATNet consistently outperforms existing advanced approaches.Ablation studies further confirm the critical roles played by the MMAD and CFFT modules to detail preservation and visual fidelity under challenging illumination-deficient environments.展开更多
High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes an...High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes and wealth of spatial details pose challenges for semantic segmentation.While convolutional neural networks(CNNs)excel at capturing local features,they are limited in modeling long-range dependencies.Conversely,transformers utilize multihead self-attention to integrate global context effectively,but this approach often incurs a high computational cost.This paper proposes a global-local multiscale context network(GLMCNet)to extract both global and local multiscale contextual information from HRSIs.A detail-enhanced filtering module(DEFM)is proposed at the end of the encoder to refine the encoder outputs further,thereby enhancing the key details extracted by the encoder and effectively suppressing redundant information.In addition,a global-local multiscale transformer block(GLMTB)is proposed in the decoding stage to enable the modeling of rich multiscale global and local information.We also design a stair fusion mechanism to transmit deep semantic information from deep to shallow layers progressively.Finally,we propose the semantic awareness enhancement module(SAEM),which further enhances the representation of multiscale semantic features through spatial attention and covariance channel attention.Extensive ablation analyses and comparative experiments were conducted to evaluate the performance of the proposed method.Specifically,our method achieved a mean Intersection over Union(mIoU)of 86.89%on the ISPRS Potsdam dataset and 84.34%on the ISPRS Vaihingen dataset,outperforming existing models such as ABCNet and BANet.展开更多
Driven by advancements in mobile internet technology,images have become a crucial data medium.Ensuring the security of image information during transmission has thus emerged as an urgent challenge.This study proposes ...Driven by advancements in mobile internet technology,images have become a crucial data medium.Ensuring the security of image information during transmission has thus emerged as an urgent challenge.This study proposes a novel image encryption algorithm specifically designed for grayscale image security.This research introduces a new Cantor diagonal matrix permutation method.The proposed permutation method uses row and column index sequences to control the Cantor diagonal matrix,where the row and column index sequences are generated by a spatiotemporal chaotic system named coupled map lattice(CML).The high initial value sensitivity of the CML system makes the permutation method highly sensitive and secure.Additionally,leveraging fractal theory,this study introduces a chaotic fractal matrix and applies this matrix in the diffusion process.This chaotic fractal matrix exhibits selfsimilarity and irregularity.Using the Cantor diagonal matrix and chaotic fractal matrix,this paper introduces a fast image encryption algorithm involving two diffusion steps and one permutation step.Moreover,the algorithm achieves robust security with only a single encryption round,ensuring high operational efficiency.Experimental results show that the proposed algorithm features an expansive key space,robust security,high sensitivity,high efficiency,and superior statistical properties for the ciphered images.Thus,the proposed algorithm not only provides a practical solution for secure image transmission but also bridges fractal theory with image encryption techniques,thereby opening new research avenues in chaotic cryptography and advancing the development of information security technology.展开更多
Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi...Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi-stego images provides good image quality but often results in low embedding capability.To address these challenges,this paper proposes a high-capacity RDH scheme based on PVO that generates three stego images from a single cover image.The cover image is partitioned into non-overlapping blocks with pixels sorted in ascending order.Four secret bits are embedded into each block’s maximum pixel value,while three additional bits are embedded into the second-largest value when the pixel difference exceeds a predefined threshold.A similar embedding strategy is also applied to the minimum side of the block,including the second-smallest pixel value.This design enables each block to embed up to 14 bits of secret data.Experimental results demonstrate that the proposed method achieves significantly higher embedding capacity and improved visual quality compared to existing triple-stego RDH approaches,advancing the field of reversible steganography.展开更多
Photoresponsive memristors(i.e.,photomemristors)have been recently highly regarded to tackle data latency and energy consumption challenges in conventional Von Neumann architecture-based image recognition systems.Howe...Photoresponsive memristors(i.e.,photomemristors)have been recently highly regarded to tackle data latency and energy consumption challenges in conventional Von Neumann architecture-based image recognition systems.However,their efficacy in recognizing low-contrast images is quite limited,and while preprocessing algorithms are usually employed to enhance these images,which naturally introduce delays that hinder real-time recognition in complex conditions.To address this challenge,here we present a selfdriven polarization-sensitive ferroelectric photomemristor inspired by advanced biological systems.The proposed prototype device is engineered to extract image polarization information,enabling real-time and in-situ enhanced image recognition and classification capabilities.By combining the anisotropic optical feature of the two-dimensional material(ReSe_(2))and ferroelectric polarization of singlecrystalline diisopropylammonium bromide(DIPAB)thin film,tunable and self-driven polarized responsiveness with intelligence was achieved.With remarkable optoelectronic synaptic characteristics of the fabricated device,a significant enhancement was demonstrated in recognition probability—averaging an impressive 85.9% for low-contrast scenarios,in contrast to the mere 47.5% exhibited by traditional photomemristors.This holds substantial implications for the detection and recognition of subtle information in diverse scenes such as autonomous driving,medical imaging,and astronomical observation.展开更多
Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods ex...Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods exhibit deficiencies in detail recovery and noise suppression,particularly when processing complex landscapes(e.g.,forests,farmlands),leading to artifacts and spectral distortions that limit practical utility.To address this,we propose an enhanced Super-Resolution Generative Adversarial Network(SRGAN)framework featuring three key innovations:(1)Replacement of L1/L2 loss with a robust Charbonnier loss to suppress noise while preserving edge details via adaptive gradient balancing;(2)A multi-loss joint optimization strategy dynamically weighting Charbonnier loss(β=0.5),Visual Geometry Group(VGG)perceptual loss(α=1),and adversarial loss(γ=0.1)to synergize pixel-level accuracy and perceptual quality;(3)A multi-scale residual network(MSRN)capturing cross-scale texture features(e.g.,forest canopies,mountain contours).Validated on Sentinel-2(10 m)and SPOT-6/7(2.5 m)datasets covering 904 km2 in Motuo County,Xizang,our method outperforms the SRGAN baseline(SR4RS)with Peak Signal-to-Noise Ratio(PSNR)gains of 0.29 dB and Structural Similarity Index(SSIM)improvements of 3.08%on forest imagery.Visual comparisons confirm enhanced texture continuity despite marginal Learned Perceptual Image Patch Similarity(LPIPS)increases.The method significantly improves noise robustness and edge retention in complex geomorphology,demonstrating 18%faster response in forest fire early warning and providing high-resolution support for agricultural/urban monitoring.Future work will integrate spectral constraints and lightweight architectures.展开更多
Colorectal cancer(CRC)with lung oligometastases,particularly in the presence of extrapulmonary disease,poses considerable therapeutic challenges in clinical practice.We have carefully studied the multicenter study by ...Colorectal cancer(CRC)with lung oligometastases,particularly in the presence of extrapulmonary disease,poses considerable therapeutic challenges in clinical practice.We have carefully studied the multicenter study by Hu et al,which evaluated the survival outcomes of patients with metastatic CRC who received image-guided thermal ablation(IGTA).These findings provide valuable clinical evidence supporting IGTA as a feasible,minimally invasive approach and underscore the prognostic significance of metastatic distribution.However,the study by Hu et al has several limitations,including that not all pulmonary lesions were pathologically confirmed,postoperative follow-up mainly relied on dynamic contrast-enhanced computed tomography,no comparative analysis was performed with other local treatments,and the impact of other imaging features on efficacy and prognosis was not evaluated.Future studies should include complete pathological confirmation,integrate functional imaging and radiomics,and use prospective multicenter collaboration to optimize patient selection standards for IGTA treatment,strengthen its clinical evidence base,and ultimately promote individualized decision-making for patients with metastatic CRC.展开更多
Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often stru...Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often struggle with low-contrast MRI images,class imbalance,and suboptimal feature extraction.This paper develops a Hybrid DL system that unites MobileNetV2 with adaptive classification methods to boost Alzheimer’s diagnosis by processing MRI scans.Image enhancement is done using Contrast-Limited Adaptive Histogram Equalization(CLAHE)and Enhanced Super-Resolution Generative Adversarial Networks(ESRGAN).A classification robustness enhancement system integrates class weighting techniques and a Matthews Correlation Coefficient(MCC)-based evaluation method into the design.The trained and validated model gives a 98.88%accuracy rate and 0.9614 MCC score.We also performed a 10-fold cross-validation experiment with an average accuracy of 96.52%(±1.51),a loss of 0.1671,and an MCC score of 0.9429 across folds.The proposed framework outperforms the state-of-the-art models with a 98%weighted F1-score while decreasing misdiagnosis results for every AD stage.The model demonstrates apparent separation abilities between AD progression stages according to the results of the confusion matrix analysis.These results validate the effectiveness of hybrid DL models with adaptive preprocessing for early and reliable Alzheimer’s diagnosis,contributing to improved computer-aided diagnosis(CAD)systems in clinical practice.展开更多
Dear editor,Cross-modal retrieval in remote sensing(RS) data has inspired increasing enthusiasm due to its merit in flexible input and efficient query. In this letter, we address to establish semantic relationship bet...Dear editor,Cross-modal retrieval in remote sensing(RS) data has inspired increasing enthusiasm due to its merit in flexible input and efficient query. In this letter, we address to establish semantic relationship between RS images and their description sentences.展开更多
Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security.Currently,with the emergence of massive high-resolution multi...Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security.Currently,with the emergence of massive high-resolution multi-modality images,the use of multi-modality images for fine-grained recognition has become a promising technology.Fine-grained recognition of multi-modality images imposes higher requirements on the dataset samples.The key to the problem is how to extract and fuse the complementary features of multi-modality images to obtain more discriminative fusion features.The attention mechanism helps the model to pinpoint the key information in the image,resulting in a significant improvement in the model’s performance.In this paper,a dataset for fine-grained recognition of ships based on visible and near-infrared multi-modality remote sensing images has been proposed first,named Dataset for Multimodal Fine-grained Recognition of Ships(DMFGRS).It includes 1,635 pairs of visible and near-infrared remote sensing images divided into 20 categories,collated from digital orthophotos model provided by commercial remote sensing satellites.DMFGRS provides two types of annotation format files,as well as segmentation mask images corresponding to the ship targets.Then,a Multimodal Information Cross-Enhancement Network(MICE-Net)fusing features of visible and near-infrared remote sensing images,has been proposed.In the network,a dual-branch feature extraction and fusion module has been designed to obtain more expressive features.The Feature Cross Enhancement Module(FCEM)achieves the fusion enhancement of the two modal features by making the channel attention and spatial attention work cross-functionally on the feature map.A benchmark is established by evaluating state-of-the-art object recognition algorithms on DMFGRS.MICE-Net conducted experiments on DMFGRS,and the precision,recall,mAP0.5 and mAP0.5:0.95 reached 87%,77.1%,83.8%and 63.9%,respectively.Extensive experiments demonstrate that the proposed MICE-Net has more excellent performance on DMFGRS.Built on lightweight network YOLO,the model has excellent generalizability,and thus has good potential for application in real-life scenarios.展开更多
基金Supported by the National Natural Science Foundation of China(61601176)。
文摘In this paper,we propose hierarchical attention dual network(DNet)for fine-grained image classification.The DNet can randomly select pairs of inputs from the dataset and compare the differences between them through hierarchical attention feature learning,which are used simultaneously to remove noise and retain salient features.In the loss function,it considers the losses of difference in paired images according to the intra-variance and inter-variance.In addition,we also collect the disaster scene dataset from remote sensing images and apply the proposed method to disaster scene classification,which contains complex scenes and multiple types of disasters.Compared to other methods,experimental results show that the DNet with hierarchical attention is robust to different datasets and performs better.
基金This research was funded by King Mongkut’s University of Technology North Bangkok(Contract no.KMUTNB-62-KNOW-026).
文摘Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scales.A cul-tural heritage image is one of thefine-grained images because each image has the same similarity in most cases.Using the classification technique,distinguishing cultural heritage architecture may be difficult.This study proposes a cultural heri-tage content retrieval method using adaptive deep learning forfine-grained image retrieval.The key contribution of this research was the creation of a retrieval mod-el that could handle incremental streams of new categories while maintaining its past performance in old categories and not losing the old categorization of a cul-tural heritage image.The goal of the proposed method is to perform a retrieval task for classes.Incremental learning for new classes was conducted to reduce the re-training process.In this step,the original class is not necessary for re-train-ing which we call an adaptive deep learning technique.Cultural heritage in the case of Thai archaeological site architecture was retrieved through machine learn-ing and image processing.We analyze the experimental results of incremental learning forfine-grained images with images of Thai archaeological site architec-ture from world heritage provinces in Thailand,which have a similar architecture.Using afine-grained image retrieval technique for this group of cultural heritage images in a database can solve the problem of a high degree of similarity among categories and a high degree of dissimilarity for a specific category.The proposed method for retrieving the correct image from a database can deliver an average accuracy of 85 percent.Adaptive deep learning forfine-grained image retrieval was used to retrieve cultural heritage content,and it outperformed state-of-the-art methods infine-grained image retrieval.
文摘Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.
基金supported by the National Natural Science Foundation of China,China (Grants No.62171232)the Priority Academic Program Development of Jiangsu Higher Education Institutions,China。
文摘Fine-grained Image Recognition(FGIR)task is dedicated to distinguishing similar sub-categories that belong to the same super-category,such as bird species and car types.In order to highlight visual differences,existing FGIR works often follow two steps:discriminative sub-region localization and local feature representation.However,these works pay less attention on global context information.They neglect a fact that the subtle visual difference in challenging scenarios can be highlighted through exploiting the spatial relationship among different subregions from a global view point.Therefore,in this paper,we consider both global and local information for FGIR,and propose a collaborative teacher-student strategy to reinforce and unity the two types of information.Our framework is implemented mainly by convolutional neural network,referred to Teacher-Student Based Attention Convolutional Neural Network(T-S-ACNN).For fine-grained local information,we choose the classic Multi-Attention Network(MA-Net)as our baseline,and propose a type of boundary constraint to further reduce background noises in the local attention maps.In this way,the discriminative sub-regions tend to appear in the area occupied by fine-grained objects,leading to more accurate sub-region localization.For fine-grained global information,we design a graph convolution based Global Attention Network(GA-Net),which can combine extracted local attention maps from MA-Net with non-local techniques to explore spatial relationship among subregions.At last,we develop a collaborative teacher-student strategy to adaptively determine the attended roles and optimization modes,so as to enhance the cooperative reinforcement of MA-Net and GA-Net.Extensive experiments on CUB-200-2011,Stanford Cars and FGVC Aircraft datasets illustrate the promising performance of our framework.
基金supported by the Dalian Youth Science and Technology Star Program under Grant No.2023RQ014the Basic Education Project of Liaoning Province of China under Grant No.JYTQN2023101+2 种基金the Interdisciplinary Project of Dalian University under Grant No.DLUXK-2023-QN-016the Support Plan for Key Field Innovation Team of Dalian under Grant No.2021RT06the 111 Project of China under Grant No.D23006.
文摘Low-resolution(LR)fine-grained image recognition requires the ability to recognize the subcategories of LR samples with limited fine-grained details.The existing methods do not make full use of the guiding and constraining capabilities of category-related knowledge to recover and extract the fine-grained features of LR data;thus these methods have a limited ability to learn the global and local fine-grained features of LR data.In this paper,we propose an enhanced feature representation network(EFR-Net)based on categorical knowledge guidance to capture delicate and reliable fine-grained feature descriptions of LR data and improve the recognition accuracy.First,to overcome the challenges posed by the limited fine-grained details in LR data,we design a classwise distillation loss.This loss function transfers the high-quality features of class-specific high-resolution(HR)samples into the feature learning of the same-category LR samples by using a memory bank.In this way,the global representation of LR images is closer to the meaningful and high-quality image features.Second,considering that fine-grained discriminative features are often hidden in object parts,we present a group of part queries to learn the positional information where the discriminative cues exist across all categories,and we then use the queries to decode diverse and discriminative part features.The global representation,in combination with the local discriminative features,creates more comprehensive and meaningful feature descriptions of the LR fine-grained objects,thus improving the recognition performance.Extensive comparison experiments on four LR datasets demonstrate the effectiveness of EFR-Net.
基金supported by the National Natural Science Foundation of China(Nos.62372266,61832012,12271295,and 62072273)the Natural Science Foundation of Shandong Province(Nos.ZR2020MF149,ZR2022MF304,ZR2021MF075,ZR2021QF050,and ZR2019ZD10)the Key Research and Development Program Project of Shandong Province(No.2022CXPT055).
文摘Finding more specific subcategories within a larger category is the goal of fine-grained image classification(FGIC),and the key is to find local discriminative regions of visual features.Most existing methods use traditional convolutional operations to achieve fine-grained image classification.However,traditional convolution cannot extract multi-scale features of an image and existing methods are susceptible to interference from image background information.Therefore,to address the above problems,this paper proposes an FGIC model(Attention-PCNN)based on hybrid attention mechanism and pyramidal convolution.The model feeds the multi-scale features extracted by the pyramidal convolutional neural network into two branches capturing global and local information respectively.In particular,a hybrid attention mechanism is added to the branch capturing global information in order to reduce the interference of image background information and make the model pay more attention to the target region with fine-grained features.In addition,the mutual-channel loss(MC-LOSS)is introduced in the local information branch to capture fine-grained features.We evaluated the model on three publicly available datasets CUB-200-2011,Stanford Cars,FGVCAircraft,etc.Compared to the state-of-the-art methods,the results show that Attention-PCNN performs better.
基金supported by the National Natural Science Foundation of China(42030102,42371321).
文摘Accurate fine-grained geospatial scene classification using remote sensing imagery is essential for a wide range of applications.However,existing approaches often rely on manually zooming remote sensing images at different scales to create typical scene samples.This approach fails to adequately support the fixed-resolution image interpretation requirements in real-world scenarios.To address this limitation,we introduce the million-scale fine-grained geospatial scene classification dataset(MEET),which contains over 1.03 million zoom-free remote sensing scene samples,manually annotated into 80 fine-grained categories.In MEET,each scene sample follows a scene-in-scene layout,where the central scene serves as the reference,and auxiliary scenes provide crucial spatial context for fine-grained classification.Moreover,to tackle the emerging challenge of scene-in-scene classification,we present the context-aware transformer(CAT),a model specifically designed for this task,which adaptively fuses spatial context to accurately classify the scene samples.CAT adaptively fuses spatial context to accurately classify the scene samples by learning attentional features that capture the relationships between the center and auxiliary scenes.Based on MEET,we establish a comprehensive benchmark for fine-grained geospatial scene classification,evaluating CAT against 11 competitive baselines.The results demonstrate that CAT significantly outperforms these baselines,achieving a 1.88%higher balanced accuracy(BA)with the Swin-Large backbone,and a notable 7.87%improvement with the Swin-Huge backbone.Further experiments validate the effectiveness of each module in CAT and show the practical applicability of CAT in the urban functional zone mapping.The source code and dataset will be publicly available at https://jerrywyn.github.io/project/MEET.html.
基金supported by the Science and Technology Project of Henan Province(No.222102210081).
文摘Joint Multimodal Aspect-based Sentiment Analysis(JMASA)is a significant task in the research of multimodal fine-grained sentiment analysis,which combines two subtasks:Multimodal Aspect Term Extraction(MATE)and Multimodal Aspect-oriented Sentiment Classification(MASC).Currently,most existing models for JMASA only perform text and image feature encoding from a basic level,but often neglect the in-depth analysis of unimodal intrinsic features,which may lead to the low accuracy of aspect term extraction and the poor ability of sentiment prediction due to the insufficient learning of intra-modal features.Given this problem,we propose a Text-Image Feature Fine-grained Learning(TIFFL)model for JMASA.First,we construct an enhanced adjacency matrix of word dependencies and adopt graph convolutional network to learn the syntactic structure features for text,which addresses the context interference problem of identifying different aspect terms.Then,the adjective-noun pairs extracted from image are introduced to enable the semantic representation of visual features more intuitive,which addresses the ambiguous semantic extraction problem during image feature learning.Thereby,the model performance of aspect term extraction and sentiment polarity prediction can be further optimized and enhanced.Experiments on two Twitter benchmark datasets demonstrate that TIFFL achieves competitive results for JMASA,MATE and MASC,thus validating the effectiveness of our proposed methods.
基金supported by Postgraduate Research&Practice Innovation Program of Jiangsu Province,China(Grant No.SJCX24_1332)Jiangsu Province Education Science Planning Project in 2024(Grant No.B-b/2024/01/122)High-Level Talent Scientific Research Foundation of Jinling Institute of Technology,China(Grant No.jit-b-201918).
文摘Digital watermarking technology plays an important role in detecting malicious tampering and protecting image copyright.However,in practical applications,this technology faces various problems such as severe image distortion,inaccurate localization of the tampered regions,and difficulty in recovering content.Given these shortcomings,a fragile image watermarking algorithm for tampering blind-detection and content self-recovery is proposed.The multi-feature watermarking authentication code(AC)is constructed using texture feature of local binary patterns(LBP),direct coefficient of discrete cosine transform(DCT)and contrast feature of gray level co-occurrence matrix(GLCM)for detecting the tampered region,and the recovery code(RC)is designed according to the average grayscale value of pixels in image blocks for recovering the tampered content.Optimal pixel adjustment process(OPAP)and least significant bit(LSB)algorithms are used to embed the recovery code and authentication code into the image in a staggered manner.When detecting the integrity of the image,the authentication code comparison method and threshold judgment method are used to perform two rounds of tampering detection on the image and blindly recover the tampered content.Experimental results show that this algorithm has good transparency,strong and blind detection,and self-recovery performance against four types of malicious attacks and some conventional signal processing operations.When resisting copy-paste,text addition,cropping and vector quantization under the tampering rate(TR)10%,the average tampering detection rate is up to 94.09%,and the peak signal-to-noise ratio(PSNR)of the watermarked image and the recovered image are both greater than 41.47 and 40.31 dB,which demonstrates its excellent advantages compared with other related algorithms in recent years.
基金funded by the National Natural Science Foundation of China(NNSFC)under Grant Numbers 42322408,42188101,and 42441809Additional support was provided by the Climbing Program of the National Space Science Center(NSSC,Grant No.E4PD3005)as well as the Specialized Research Fund for State Key Laboratories of China.
文摘A large-scale view of the magnetospheric cusp is expected to be obtained by the Soft X-ray Imager(SXI)onboard the Solar wind Magnetosphere Ionosphere Link Explorer(SMILE).However,it is challenging to trace the three-dimensional cusp boundary from a two-dimensional X-ray image because the detected X-ray signals will be integrated along the line of sight.In this work,a global magnetohydrodynamic code was used to simulate the X-ray images and photon count images,assuming an interplanetary magnetic field with a pure Bz component.The assumption of an elliptic cusp boundary at a given altitude was used to trace the equatorward and poleward boundaries of the cusp from a simulated X-ray image.The average discrepancy was less than 0.1 RE.To reduce the influence of instrument effects and cosmic X-ray backgrounds,image denoising was considered before applying the method above to SXI photon count images.The cusp boundaries were reasonably reconstructed from the noisy X-ray image.
基金funded by the National Natural Science Foundation of China,grant numbers 52374156 and 62476005。
文摘Images taken in dim environments frequently exhibit issues like insufficient brightness,noise,color shifts,and loss of detail.These problems pose significant challenges to dark image enhancement tasks.Current approaches,while effective in global illumination modeling,often struggle to simultaneously suppress noise and preserve structural details,especially under heterogeneous lighting.Furthermore,misalignment between luminance and color channels introduces additional challenges to accurate enhancement.In response to the aforementioned difficulties,we introduce a single-stage framework,M2ATNet,using the multi-scale multi-attention and Transformer architecture.First,to address the problems of texture blurring and residual noise,we design a multi-scale multi-attention denoising module(MMAD),which is applied separately to the luminance and color channels to enhance the structural and texture modeling capabilities.Secondly,to solve the non-alignment problem of the luminance and color channels,we introduce the multi-channel feature fusion Transformer(CFFT)module,which effectively recovers the dark details and corrects the color shifts through cross-channel alignment and deep feature interaction.To guide the model to learn more stably and efficiently,we also fuse multiple types of loss functions to form a hybrid loss term.We extensively evaluate the proposed method on various standard datasets,including LOL-v1,LOL-v2,DICM,LIME,and NPE.Evaluation in terms of numerical metrics and visual quality demonstrate that M2ATNet consistently outperforms existing advanced approaches.Ablation studies further confirm the critical roles played by the MMAD and CFFT modules to detail preservation and visual fidelity under challenging illumination-deficient environments.
基金provided by the Science Research Project of Hebei Education Department under grant No.BJK2024115.
文摘High-resolution remote sensing images(HRSIs)are now an essential data source for gathering surface information due to advancements in remote sensing data capture technologies.However,their significant scale changes and wealth of spatial details pose challenges for semantic segmentation.While convolutional neural networks(CNNs)excel at capturing local features,they are limited in modeling long-range dependencies.Conversely,transformers utilize multihead self-attention to integrate global context effectively,but this approach often incurs a high computational cost.This paper proposes a global-local multiscale context network(GLMCNet)to extract both global and local multiscale contextual information from HRSIs.A detail-enhanced filtering module(DEFM)is proposed at the end of the encoder to refine the encoder outputs further,thereby enhancing the key details extracted by the encoder and effectively suppressing redundant information.In addition,a global-local multiscale transformer block(GLMTB)is proposed in the decoding stage to enable the modeling of rich multiscale global and local information.We also design a stair fusion mechanism to transmit deep semantic information from deep to shallow layers progressively.Finally,we propose the semantic awareness enhancement module(SAEM),which further enhances the representation of multiscale semantic features through spatial attention and covariance channel attention.Extensive ablation analyses and comparative experiments were conducted to evaluate the performance of the proposed method.Specifically,our method achieved a mean Intersection over Union(mIoU)of 86.89%on the ISPRS Potsdam dataset and 84.34%on the ISPRS Vaihingen dataset,outperforming existing models such as ABCNet and BANet.
基金supported by the National Natural Science Foundation of China(62376106)The Science and Technology Development Plan of Jilin Province(20250102212JC).
文摘Driven by advancements in mobile internet technology,images have become a crucial data medium.Ensuring the security of image information during transmission has thus emerged as an urgent challenge.This study proposes a novel image encryption algorithm specifically designed for grayscale image security.This research introduces a new Cantor diagonal matrix permutation method.The proposed permutation method uses row and column index sequences to control the Cantor diagonal matrix,where the row and column index sequences are generated by a spatiotemporal chaotic system named coupled map lattice(CML).The high initial value sensitivity of the CML system makes the permutation method highly sensitive and secure.Additionally,leveraging fractal theory,this study introduces a chaotic fractal matrix and applies this matrix in the diffusion process.This chaotic fractal matrix exhibits selfsimilarity and irregularity.Using the Cantor diagonal matrix and chaotic fractal matrix,this paper introduces a fast image encryption algorithm involving two diffusion steps and one permutation step.Moreover,the algorithm achieves robust security with only a single encryption round,ensuring high operational efficiency.Experimental results show that the proposed algorithm features an expansive key space,robust security,high sensitivity,high efficiency,and superior statistical properties for the ciphered images.Thus,the proposed algorithm not only provides a practical solution for secure image transmission but also bridges fractal theory with image encryption techniques,thereby opening new research avenues in chaotic cryptography and advancing the development of information security technology.
基金funded by University of Transport and Communications(UTC)under grant number T2025-CN-004.
文摘Reversible data hiding(RDH)enables secret data embedding while preserving complete cover image recovery,making it crucial for applications requiring image integrity.The pixel value ordering(PVO)technique used in multi-stego images provides good image quality but often results in low embedding capability.To address these challenges,this paper proposes a high-capacity RDH scheme based on PVO that generates three stego images from a single cover image.The cover image is partitioned into non-overlapping blocks with pixels sorted in ascending order.Four secret bits are embedded into each block’s maximum pixel value,while three additional bits are embedded into the second-largest value when the pixel difference exceeds a predefined threshold.A similar embedding strategy is also applied to the minimum side of the block,including the second-smallest pixel value.This design enables each block to embed up to 14 bits of secret data.Experimental results demonstrate that the proposed method achieves significantly higher embedding capacity and improved visual quality compared to existing triple-stego RDH approaches,advancing the field of reversible steganography.
基金supported by the National Key Research and Development Program of China for International Cooperation under Grant 2023YFE0117100the National Natural Science Foundation of China(Nos.62074040 and 62074045).
文摘Photoresponsive memristors(i.e.,photomemristors)have been recently highly regarded to tackle data latency and energy consumption challenges in conventional Von Neumann architecture-based image recognition systems.However,their efficacy in recognizing low-contrast images is quite limited,and while preprocessing algorithms are usually employed to enhance these images,which naturally introduce delays that hinder real-time recognition in complex conditions.To address this challenge,here we present a selfdriven polarization-sensitive ferroelectric photomemristor inspired by advanced biological systems.The proposed prototype device is engineered to extract image polarization information,enabling real-time and in-situ enhanced image recognition and classification capabilities.By combining the anisotropic optical feature of the two-dimensional material(ReSe_(2))and ferroelectric polarization of singlecrystalline diisopropylammonium bromide(DIPAB)thin film,tunable and self-driven polarized responsiveness with intelligence was achieved.With remarkable optoelectronic synaptic characteristics of the fabricated device,a significant enhancement was demonstrated in recognition probability—averaging an impressive 85.9% for low-contrast scenarios,in contrast to the mere 47.5% exhibited by traditional photomemristors.This holds substantial implications for the detection and recognition of subtle information in diverse scenes such as autonomous driving,medical imaging,and astronomical observation.
基金This study was supported by:Inner Mongolia Academy of Forestry Sciences Open Research Project(Grant No.KF2024MS03)The Project to Improve the Scientific Research Capacity of the Inner Mongolia Academy of Forestry Sciences(Grant No.2024NLTS04)The Innovation and Entrepreneurship Training Program for Undergraduates of Beijing Forestry University(Grant No.X202410022268).
文摘Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods exhibit deficiencies in detail recovery and noise suppression,particularly when processing complex landscapes(e.g.,forests,farmlands),leading to artifacts and spectral distortions that limit practical utility.To address this,we propose an enhanced Super-Resolution Generative Adversarial Network(SRGAN)framework featuring three key innovations:(1)Replacement of L1/L2 loss with a robust Charbonnier loss to suppress noise while preserving edge details via adaptive gradient balancing;(2)A multi-loss joint optimization strategy dynamically weighting Charbonnier loss(β=0.5),Visual Geometry Group(VGG)perceptual loss(α=1),and adversarial loss(γ=0.1)to synergize pixel-level accuracy and perceptual quality;(3)A multi-scale residual network(MSRN)capturing cross-scale texture features(e.g.,forest canopies,mountain contours).Validated on Sentinel-2(10 m)and SPOT-6/7(2.5 m)datasets covering 904 km2 in Motuo County,Xizang,our method outperforms the SRGAN baseline(SR4RS)with Peak Signal-to-Noise Ratio(PSNR)gains of 0.29 dB and Structural Similarity Index(SSIM)improvements of 3.08%on forest imagery.Visual comparisons confirm enhanced texture continuity despite marginal Learned Perceptual Image Patch Similarity(LPIPS)increases.The method significantly improves noise robustness and edge retention in complex geomorphology,demonstrating 18%faster response in forest fire early warning and providing high-resolution support for agricultural/urban monitoring.Future work will integrate spectral constraints and lightweight architectures.
文摘Colorectal cancer(CRC)with lung oligometastases,particularly in the presence of extrapulmonary disease,poses considerable therapeutic challenges in clinical practice.We have carefully studied the multicenter study by Hu et al,which evaluated the survival outcomes of patients with metastatic CRC who received image-guided thermal ablation(IGTA).These findings provide valuable clinical evidence supporting IGTA as a feasible,minimally invasive approach and underscore the prognostic significance of metastatic distribution.However,the study by Hu et al has several limitations,including that not all pulmonary lesions were pathologically confirmed,postoperative follow-up mainly relied on dynamic contrast-enhanced computed tomography,no comparative analysis was performed with other local treatments,and the impact of other imaging features on efficacy and prognosis was not evaluated.Future studies should include complete pathological confirmation,integrate functional imaging and radiomics,and use prospective multicenter collaboration to optimize patient selection standards for IGTA treatment,strengthen its clinical evidence base,and ultimately promote individualized decision-making for patients with metastatic CRC.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01295).
文摘Alzheimer’s Disease(AD)is a progressive neurodegenerative disorder that significantly affects cognitive function,making early and accurate diagnosis essential.Traditional Deep Learning(DL)-based approaches often struggle with low-contrast MRI images,class imbalance,and suboptimal feature extraction.This paper develops a Hybrid DL system that unites MobileNetV2 with adaptive classification methods to boost Alzheimer’s diagnosis by processing MRI scans.Image enhancement is done using Contrast-Limited Adaptive Histogram Equalization(CLAHE)and Enhanced Super-Resolution Generative Adversarial Networks(ESRGAN).A classification robustness enhancement system integrates class weighting techniques and a Matthews Correlation Coefficient(MCC)-based evaluation method into the design.The trained and validated model gives a 98.88%accuracy rate and 0.9614 MCC score.We also performed a 10-fold cross-validation experiment with an average accuracy of 96.52%(±1.51),a loss of 0.1671,and an MCC score of 0.9429 across folds.The proposed framework outperforms the state-of-the-art models with a 98%weighted F1-score while decreasing misdiagnosis results for every AD stage.The model demonstrates apparent separation abilities between AD progression stages according to the results of the confusion matrix analysis.These results validate the effectiveness of hybrid DL models with adaptive preprocessing for early and reliable Alzheimer’s diagnosis,contributing to improved computer-aided diagnosis(CAD)systems in clinical practice.
基金supported by the National Natural Science Foundation of China (42090012)Special Research and 5G Project of Jiangxi Province in China (20212ABC03A09)+2 种基金Guangdong-Macao Joint Innovation Project (2021A0505080008)Key R & D Project of Sichuan Science and Technology Plan (2022YFN0031)Zhuhai Industry University Research Cooperation Project of China (ZH22017001210098PWC)。
文摘Dear editor,Cross-modal retrieval in remote sensing(RS) data has inspired increasing enthusiasm due to its merit in flexible input and efficient query. In this letter, we address to establish semantic relationship between RS images and their description sentences.
文摘Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national security.Currently,with the emergence of massive high-resolution multi-modality images,the use of multi-modality images for fine-grained recognition has become a promising technology.Fine-grained recognition of multi-modality images imposes higher requirements on the dataset samples.The key to the problem is how to extract and fuse the complementary features of multi-modality images to obtain more discriminative fusion features.The attention mechanism helps the model to pinpoint the key information in the image,resulting in a significant improvement in the model’s performance.In this paper,a dataset for fine-grained recognition of ships based on visible and near-infrared multi-modality remote sensing images has been proposed first,named Dataset for Multimodal Fine-grained Recognition of Ships(DMFGRS).It includes 1,635 pairs of visible and near-infrared remote sensing images divided into 20 categories,collated from digital orthophotos model provided by commercial remote sensing satellites.DMFGRS provides two types of annotation format files,as well as segmentation mask images corresponding to the ship targets.Then,a Multimodal Information Cross-Enhancement Network(MICE-Net)fusing features of visible and near-infrared remote sensing images,has been proposed.In the network,a dual-branch feature extraction and fusion module has been designed to obtain more expressive features.The Feature Cross Enhancement Module(FCEM)achieves the fusion enhancement of the two modal features by making the channel attention and spatial attention work cross-functionally on the feature map.A benchmark is established by evaluating state-of-the-art object recognition algorithms on DMFGRS.MICE-Net conducted experiments on DMFGRS,and the precision,recall,mAP0.5 and mAP0.5:0.95 reached 87%,77.1%,83.8%and 63.9%,respectively.Extensive experiments demonstrate that the proposed MICE-Net has more excellent performance on DMFGRS.Built on lightweight network YOLO,the model has excellent generalizability,and thus has good potential for application in real-life scenarios.
