Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image qual...Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image quality of handheld ultrasound devices is not always satisfactory due to the limited equipment size,which hinders accurate diagnoses by doctors.At the same time,paired ultrasound images are difficult to obtain from the clinic because imaging process is complicated.Therefore,we propose a modified cycle generative adversarial network(cycleGAN) for ultrasound image enhancement from multiple organs via unpaired pre-training.We introduce an ultrasound image pre-training method that does not require paired images,alleviating the requirement for large-scale paired datasets.We also propose an enhanced block with different structures in the pre-training and fine-tuning phases,which can help achieve the goals of different training phases.To improve the robustness of the model,we add Gaussian noise to the training images as data augmentation.Our approach is effective in obtaining the best quantitative evaluation results using a small number of parameters and less training costs to improve the quality of handheld ultrasound devices.展开更多
As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate unders...As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate understanding of geological reports guided by domain knowledge.While generic named entity recognition models/tools can be utilized for the processing of geoscience reports/documents,their effectiveness is hampered by a dearth of domain-specific knowledge,which in turn leads to a pronounced decline in recognition accuracy.This study summarizes six types of typical geological entities,with reference to the ontological system of geological domains and builds a high quality corpus for the task of geological named entity recognition(GNER).In addition,Geo Wo BERT-adv BGP(Geological Word-base BERTadversarial training Bi-directional Long Short-Term Memory Global Pointer)is proposed to address the issues of ambiguity,diversity and nested entities for the geological entities.The model first uses the fine-tuned word granularitybased pre-training model Geo Wo BERT(Geological Word-base BERT)and combines the text features that are extracted using the Bi LSTM(Bi-directional Long Short-Term Memory),followed by an adversarial training algorithm to improve the robustness of the model and enhance its resistance to interference,the decoding finally being performed using a global association pointer algorithm.The experimental results show that the proposed model for the constructed dataset achieves high performance and is capable of mining the rich geological information.展开更多
Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development.Traditional neural network methods,such as BiLSTM,could be ineffective due to the lack of lab data for mo...Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development.Traditional neural network methods,such as BiLSTM,could be ineffective due to the lack of lab data for model training and the overshadowing of crucial features within sequence concatenation.The current work proposes a less data-consuming model incorporating a pre-trained gene sequence model and a mutual information inference operator.Our methodology utilizes gene alignment and deduplication algorithms to preprocess gene sequences,enhancing the model’s capacity to discern and focus on distinctions among input gene pairs.The model,i.e.,DNA Pretrained Cross-Immunity Protection Inference model(DPCIPI),outperforms state-of-theart(SOTA)models in predicting hemagglutination inhibition titer from influenza viral gene sequences only.Improvement in binary cross-immunity prediction is 1.58%in F1,2.34%in precision,1.57%in recall,and 1.57%in Accuracy.For multilevel cross-immunity improvements,the improvement is 2.12%in F1,3.50%in precision,2.19%in recall,and 2.19%in Accuracy.Our study showcases the potential of pre-trained gene models to improve predictions of antigenic variation and cross-immunity.With expanding gene data and advancements in pre-trained models,this approach promises significant impacts on vaccine development and public health.展开更多
Intelligent sorting is an important prerequisite for the full quantitative consumption and harmless disposal of kitchen waste.The existing object detection method based on an ImageNet pre-trained model is an effective...Intelligent sorting is an important prerequisite for the full quantitative consumption and harmless disposal of kitchen waste.The existing object detection method based on an ImageNet pre-trained model is an effective way of sorting.Owing to significant domain gaps between natural images and kitchen waste images,it is difficult to reflect the characteristics of diverse scales and dense distribution in kitchen waste based on an ImageNet pre-trained model,leading to poor generalisation.In this article,the authors propose the first pre-trained model for kitchen waste sorting called KitWaSor,which combines both contrastive learning(CL)and masked image modelling(MIM)through self-supervised learning(SSL).First,to address the issue of diverse scales,the authors propose a mixed masking strategy by introducing an incomplete masking branch based on the original random masking branch.It prevents the complete loss of small-scale objects while avoiding excessive leakage of large-scale object pixels.Second,to address the issue of dense distribution,the authors introduce semantic consistency constraints on the basis of the mixed masking strategy.That is,object semantic reasoning is performed through semantic consistency constraints to compensate for the lack of contextual information.To train KitWaSor,the authors construct the first million-level kitchen waste dataset across seasonal and regional distributions,named KWD-Million.Extensive experiments show that KitWaSor achieves state-of-the-art(SOTA)performance on the two most relevant downstream tasks for kitchen waste sorting(i.e.image classification and object detection),demonstrating the effectiveness of the proposed KitWaSor.展开更多
Deep neural networks provide accurate results for most applications.However,they need a big dataset to train properly.Providing a big dataset is a significant challenge in most applications.Image augmentation refers t...Deep neural networks provide accurate results for most applications.However,they need a big dataset to train properly.Providing a big dataset is a significant challenge in most applications.Image augmentation refers to techniques that increase the amount of image data.Common operations for image augmentation include changes in illumination,rotation,contrast,size,viewing angle,and others.Recently,Generative Adversarial Networks(GANs)have been employed for image generation.However,like image augmentation methods,GAN approaches can only generate images that are similar to the original images.Therefore,they also cannot generate new classes of data.Texture images presentmore challenges than general images,and generating textures is more complex than creating other types of images.This study proposes a gradient-based deep neural network method that generates a new class of texture.It is possible to rapidly generate new classes of textures using different kernels from pre-trained deep networks.After generating new textures for each class,the number of textures increases through image augmentation.During this process,several techniques are proposed to automatically remove incomplete and similar textures that are created.The proposed method is faster than some well-known generative networks by around 4 to 10 times.In addition,the quality of the generated textures surpasses that of these networks.The proposed method can generate textures that surpass those of someGANs and parametric models in certain image qualitymetrics.It can provide a big texture dataset to train deep networks.A new big texture dataset is created artificially using the proposed method.This dataset is approximately 2 GB in size and comprises 30,000 textures,each 150×150 pixels in size,organized into 600 classes.It is uploaded to the Kaggle site and Google Drive.This dataset is called BigTex.Compared to other texture datasets,the proposed dataset is the largest and can serve as a comprehensive texture dataset for training more powerful deep neural networks and mitigating overfitting.展开更多
We analyze the suitability of existing pre-trained transformer-based language models(PLMs)for abstractive text summarization on German technical healthcare texts.The study focuses on the multilingual capabilities of t...We analyze the suitability of existing pre-trained transformer-based language models(PLMs)for abstractive text summarization on German technical healthcare texts.The study focuses on the multilingual capabilities of these models and their ability to perform the task of abstractive text summarization in the healthcare field.The research hypothesis was that large language models could perform high-quality abstractive text summarization on German technical healthcare texts,even if the model is not specifically trained in that language.Through experiments,the research questions explore the performance of transformer language models in dealing with complex syntax constructs,the difference in performance between models trained in English and German,and the impact of translating the source text to English before conducting the summarization.We conducted an evaluation of four PLMs(GPT-3,a translation-based approach also utilizing GPT-3,a German language Model,and a domain-specific bio-medical model approach).The evaluation considered the informativeness using 3 types of metrics based on Recall-Oriented Understudy for Gisting Evaluation(ROUGE)and the quality of results which is manually evaluated considering 5 aspects.The results show that text summarization models could be used in the German healthcare domain and that domain-independent language models achieved the best results.The study proves that text summarization models can simplify the search for pre-existing German knowledge in various domains.展开更多
How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classif...How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.展开更多
Vision-Language-Navigation(VLN) task is a cross-modality task that combines natural language processing and computer vision. This task requires the agent to automatically move to the destination according to the natur...Vision-Language-Navigation(VLN) task is a cross-modality task that combines natural language processing and computer vision. This task requires the agent to automatically move to the destination according to the natural language instruction and the observed surrounding visual information. To make the best decision, in every step during the navigation, the agent should pay more attention to understanding the objects, the object attributes, and the object relationships. But most current methods process all received textual and visual information equally. Therefore, this paper integrates more detailed semantic connections between visual and textual information through three pre-training tasks(object prediction, object attributes prediction, and object relationship prediction). The model will learn better fusion representation and alignment between these two types of information to improve the success rate(SR) and generalization. The experiments show that compared with the former baseline models, the SR on the unseen validation set(Val Unseen) increased by 7%, and the SR weighted by path length(SPL) increased by 7%;the SR on the test set(Test) increased 4%, SPL increased by 3%.展开更多
Web-based training is growing quickly in popularit y for professionals in industrial organizations and large enterprises. The savings in cost and time are significant. The instructor-led trainings are bounded by time ...Web-based training is growing quickly in popularit y for professionals in industrial organizations and large enterprises. The savings in cost and time are significant. The instructor-led trainings are bounded by time and place, not to mention the cost involved in traveling, accommodation and training venue. However, in the most online training courses, all trainees are given same training materials and teaching paradigms. The problem of differentia ting the trainees’ abilities is the main concern. We need a pre-training test t o identify and classify of the weaknesses and strengths of differentiate trainee s so as to devise an appropriate training programs for the trainees. Adaptation of a Web-based Computer adaptive Test (CAT) for the pre-training test make the web-based training more efficient. The advantages of CAT are self-pacing, eff iciency, time and cost saving, immediate scoring and feedback, accuracy and secu rity, etc (Rudner, 1998; UMN, 1999; Novell, 2000; Linacre, 2000; Windowsglore, 2 000). Moreover, Web-based CAT also gives greater flexibility and convenience. T his paper describes how this CAT tool is built, how it helps instructor identify the strengths and weaknesses of trainees, and how to assure quality on the CAT system.展开更多
Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requir...Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.展开更多
We present an approach to classify medical text at a sentence level automatically.Given the inherent complexity of medical text classification,we employ adapters based on pre-trained language models to extract informa...We present an approach to classify medical text at a sentence level automatically.Given the inherent complexity of medical text classification,we employ adapters based on pre-trained language models to extract information from medical text,facilitating more accurate classification while minimizing the number of trainable parameters.Extensive experiments conducted on various datasets demonstrate the effectiveness of our approach.展开更多
In multimodal learning, Vision-Language Models (VLMs) have become a critical research focus, enabling the integration of textual and visual data. These models have shown significant promise across various natural lang...In multimodal learning, Vision-Language Models (VLMs) have become a critical research focus, enabling the integration of textual and visual data. These models have shown significant promise across various natural language processing tasks, such as visual question answering and computer vision applications, including image captioning and image-text retrieval, highlighting their adaptability for complex, multimodal datasets. In this work, we review the landscape of Bootstrapping Language-Image Pre-training (BLIP) and other VLM techniques. A comparative analysis is conducted to assess VLMs’ strengths, limitations, and applicability across tasks while examining challenges such as scalability, data quality, and fine-tuning complexities. The work concludes by outlining potential future directions in VLM research, focusing on enhancing model interpretability, addressing ethical implications, and advancing multimodal integration in real-world applications.展开更多
Coarse-grained soils are fundamental to major infrastructures like embankments,roads,and bridges.Understanding their deformation characteristics is essential for ensuring structural stability.Traditional methods,such ...Coarse-grained soils are fundamental to major infrastructures like embankments,roads,and bridges.Understanding their deformation characteristics is essential for ensuring structural stability.Traditional methods,such as triaxial compression tests and numerical simulations,face challenges like high costs,time consumption,and limited generalizability across different soils and conditions.To address these limitations,this study employs deep learning to predict the volumetric strain of coarse-grained soils as axial strain changes,aiming to obtain the axial strain(ε_(a))-volumetric strain(ε_(v))curve,which helps derive key mechanical parameters like cohesion(c),and elastic modulus(E).However,the limited data from triaxial tests poses challenges for training deep learning models.We propose using a Time-series Generative Adversarial Network(TimeGAN)for data augmentation.Additionally,we apply feature importance analysis to assess the quality of the numerical augmented data,providing feedback for improving the TimeGAN model.To further enhance model performance,we introduce the pre-training strategy to reduce bias between augmented and real data.Experimental results demonstrate that our approach effectively predictscurve,with the mean absolute error(MAE)of 0.2219 and the R^(2) of 0.9155.The analysis aligns with established findings in soil mechanics,underscoring the potential of our method in engineering applications.展开更多
Cyberbullying is a remarkable issue in the Arabic-speaking world,affecting children,organizations,and businesses.Various efforts have been made to combat this problem through proposed models using machine learning(ML)...Cyberbullying is a remarkable issue in the Arabic-speaking world,affecting children,organizations,and businesses.Various efforts have been made to combat this problem through proposed models using machine learning(ML)and deep learning(DL)approaches utilizing natural language processing(NLP)methods and by proposing relevant datasets.However,most of these endeavors focused predominantly on the English language,leaving a substantial gap in addressing Arabic cyberbullying.Given the complexities of the Arabic language,transfer learning techniques and transformers present a promising approach to enhance the detection and classification of abusive content by leveraging large and pretrained models that use a large dataset.Therefore,this study proposes a hybrid model using transformers trained on extensive Arabic datasets.It then fine-tunes the hybrid model on a newly curated Arabic cyberbullying dataset collected from social media platforms,in particular Twitter.Additionally,the following two hybrid transformer models are introduced:the first combines CAmelid Morphologically-aware pretrained Bidirectional Encoder Representations from Transformers(CAMeLBERT)with Arabic Generative Pre-trained Transformer 2(AraGPT2)and the second combines Arabic BERT(AraBERT)with Cross-lingual Language Model-RoBERTa(XLM-R).Two strategies,namely,feature fusion and ensemble voting,are employed to improve the model performance accuracy.Experimental results,measured through precision,recall,F1-score,accuracy,and AreaUnder the Curve-Receiver Operating Characteristic(AUC-ROC),demonstrate that the combined CAMeLBERT and AraGPT2 models using feature fusion outperformed traditional DL models,such as Long Short-Term Memory(LSTM)and Bidirectional Long Short-Term Memory(BiLSTM),as well as other independent Arabic-based transformer models.展开更多
Entity relation extraction,a fundamental and essential task in natural language processing(NLP),has garnered significant attention over an extended period.,aiming to extract the core of semantic knowledge from unstruc...Entity relation extraction,a fundamental and essential task in natural language processing(NLP),has garnered significant attention over an extended period.,aiming to extract the core of semantic knowledge from unstructured text,i.e.,entities and the relations between them.At present,the main dilemma of Chinese entity relation extraction research lies in nested entities,relation overlap,and lack of entity relation interaction.This dilemma is particularly prominent in complex knowledge extraction tasks with high-density knowledge,imprecise syntactic structure,and lack of semantic roles.To address these challenges,this paper presents an innovative“character-level”Chinese part-of-speech(CN-POS)tagging approach and incorporates part-of-speech(POS)information into the pre-trained model,aiming to improve its semantic understanding and syntactic information processing capabilities.Additionally,A relation reference filling mechanism(RF)is proposed to enhance the semantic interaction between relations and entities,utilize relations to guide entity modeling,improve the boundary prediction ability of entity models for nested entity phenomena,and increase the cascading accuracy of entity-relation triples.Meanwhile,the“Queue”sub-task connection strategy is adopted to alleviate triplet cascading errors caused by overlapping relations,and a Syntax-enhanced entity relation extraction model(SE-RE)is constructed.The model showed excellent performance on the self-constructed E-commerce Product Information dataset(EPI)in this article.The results demonstrate that integrating POS enhancement into the pre-trained encoding model significantly boosts the performance of entity relation extraction models compared to baseline methods.Specifically,the F1-score fluctuation in subtasks caused by error accumulation was reduced by 3.21%,while the F1-score for entity-relation triplet extraction improved by 1.91%.展开更多
In the Visual Place Recognition(VPR)task,existing research has leveraged large-scale pre-trained models to improve the performance of place recognition.However,when there are significant environmental differences betw...In the Visual Place Recognition(VPR)task,existing research has leveraged large-scale pre-trained models to improve the performance of place recognition.However,when there are significant environmental differences between query images and reference images,a large number of ineffective local features will interfere with the extraction of key landmark features,leading to the retrieval of visually similar but geographically different images.To address this perceptual aliasing problem caused by environmental condition changes,we propose a novel Visual Place Recognition method with Cross-Environment Robust Feature Enhancement(CerfeVPR).This method uses the GAN network to generate similar images of the original images under different environmental conditions,thereby enhancing the learning of robust features of the original images.This enables the global descriptor to effectively ignore appearance changes caused by environmental factors such as seasons and lighting,showing better place recognition accuracy than other methods.Meanwhile,we introduce a large kernel convolution adapter to fine tune the pre-trained model,obtaining a better image feature representation for subsequent robust feature learning.Then,we process the information of different local regions in the general features through a 3-layer pyramid scene parsing network and fuse it with a tag that retains global information to construct a multi-dimensional image feature representation.Based on this,we use the fused features of similar images to drive the robust feature learning of the original images and complete the feature matching between query images and retrieved images.Experiments on multiple commonly used datasets show that our method exhibits excellent performance.On average,CerfeVPR achieves the highest results,with all Recall@N values exceeding 90%.In particular,on the highly challenging Nordland dataset,the R@1 metric is improved by 4.6%,significantly outperforming other methods,which fully verifies the superiority of CerfeVPR in visual place recognition under complex environments.展开更多
Existing image manipulation localization(IML)techniques require large,densely annotated sets of forged images.This requirement greatly increases labeling costs and limits a model’s ability to handle manipulation type...Existing image manipulation localization(IML)techniques require large,densely annotated sets of forged images.This requirement greatly increases labeling costs and limits a model’s ability to handle manipulation types that are novel or absent from the training data.To address these issues,we present CLIP-IML,an IML framework that leverages contrastive language-image pre-training(CLIP).A lightweight feature-reconstruction module transforms CLIP token sequences into spatial tensors,after which a compact feature-pyramid network and a multi-scale fusion decoder work together to capture information from fine to coarse levels.We evaluated CLIP-IML on ten public datasets that cover copy-move,splicing,removal,and artificial intelligence(AI)-generated forgeries.The framework raises the average F1-score by 7.85%relative to the strongest recent baselines and secures either the first-or second-place performance on every dataset.Ablation studies show that CLIP pre-training,higher resolution inputs,and the multi-scale decoder each make complementary contributions.Under six common post-processing perturbations,as well as the compression pipelines used by Facebook,Weibo,and WeChat,the performance decline never exceeds 2.2%,confirming strong practical robustness.Moreover,CLIP-IML requires only a few thousand annotated images for training,which markedly reduces data-collection and labeling effort compared with previous methods.All of these results indicate that CLIP-IML is highly generalizable for image tampering localization across a wide range of tampering scenarios.展开更多
Early exiting has shown significant potential in accelerating the inference of pre-trained language models(PLMs)by allowing easy samples to exit from shallow layers.However,existing early exiting methods primarily rel...Early exiting has shown significant potential in accelerating the inference of pre-trained language models(PLMs)by allowing easy samples to exit from shallow layers.However,existing early exiting methods primarily rely on local information from individual samples to estimate prediction uncertainty for making exiting decisions,overlooking the global information provided by the sample population.This impacts the estimation of prediction uncertainty,compromising the reliability of exiting de-cisions.To remedy this,inspired by principal component analysis(PCA),the authors define a residual score to capture the deviation of features from the principal space of the sample population,providing a global perspective for estimating prediction uncertainty.Building on this,a two-stage exiting strategy is proposed that integrates global information from residual scores with local information from energy scores at both the decision and feature levels.This strategy incorporates three-way decisions to enable more reliable exiting decisions for boundary region samples by delaying judgement.Extensive experiments on the GLUE benchmark validate that the method achieves an average speed-up ratio of 2.17×across all tasks with minimal per-formance degradation.Additionally,it surpasses the state-of-the-art E-LANG by 11%in model acceleration,along with a performance improvement of 0.6 points,demonstrating a better performance-efficiency trade-off.展开更多
In task-oriented dialogue systems, intent, emotion, and actions are crucial elements of user activity. Analyzing the relationships among these elements to control and manage task-oriented dialogue systems is a challen...In task-oriented dialogue systems, intent, emotion, and actions are crucial elements of user activity. Analyzing the relationships among these elements to control and manage task-oriented dialogue systems is a challenging task. However, previous work has primarily focused on the independent recognition of user intent and emotion, making it difficult to simultaneously track both aspects in the dialogue tracking module and to effectively utilize user emotions in subsequent dialogue strategies. We propose a Multi-Head Encoder Shared Model (MESM) that dynamically integrates features from emotion and intent encoders through a feature fusioner. Addressing the scarcity of datasets containing both emotion and intent labels, we designed a multi-dataset learning approach enabling the model to generate dialogue summaries encompassing both user intent and emotion. Experiments conducted on the MultiWoZ and MELD datasets demonstrate that our model effectively captures user intent and emotion, achieving extremely competitive results in dialogue state tracking tasks.展开更多
文摘Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image quality of handheld ultrasound devices is not always satisfactory due to the limited equipment size,which hinders accurate diagnoses by doctors.At the same time,paired ultrasound images are difficult to obtain from the clinic because imaging process is complicated.Therefore,we propose a modified cycle generative adversarial network(cycleGAN) for ultrasound image enhancement from multiple organs via unpaired pre-training.We introduce an ultrasound image pre-training method that does not require paired images,alleviating the requirement for large-scale paired datasets.We also propose an enhanced block with different structures in the pre-training and fine-tuning phases,which can help achieve the goals of different training phases.To improve the robustness of the model,we add Gaussian noise to the training images as data augmentation.Our approach is effective in obtaining the best quantitative evaluation results using a small number of parameters and less training costs to improve the quality of handheld ultrasound devices.
基金financially supported by the Natural Science Foundation of China(Grant No.42301492)the National Key R&D Program of China(Grant Nos.2022YFF0711600,2022YFF0801201,2022YFF0801200)+3 种基金the Major Special Project of Xinjiang(Grant No.2022A03009-3)the Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation,Ministry of Natural Resources(Grant No.KF-2022-07014)the Opening Fund of the Key Laboratory of the Geological Survey and Evaluation of the Ministry of Education(Grant No.GLAB 2023ZR01)the Fundamental Research Funds for the Central Universities。
文摘As important geological data,a geological report contains rich expert and geological knowledge,but the challenge facing current research into geological knowledge extraction and mining is how to render accurate understanding of geological reports guided by domain knowledge.While generic named entity recognition models/tools can be utilized for the processing of geoscience reports/documents,their effectiveness is hampered by a dearth of domain-specific knowledge,which in turn leads to a pronounced decline in recognition accuracy.This study summarizes six types of typical geological entities,with reference to the ontological system of geological domains and builds a high quality corpus for the task of geological named entity recognition(GNER).In addition,Geo Wo BERT-adv BGP(Geological Word-base BERTadversarial training Bi-directional Long Short-Term Memory Global Pointer)is proposed to address the issues of ambiguity,diversity and nested entities for the geological entities.The model first uses the fine-tuned word granularitybased pre-training model Geo Wo BERT(Geological Word-base BERT)and combines the text features that are extracted using the Bi LSTM(Bi-directional Long Short-Term Memory),followed by an adversarial training algorithm to improve the robustness of the model and enhance its resistance to interference,the decoding finally being performed using a global association pointer algorithm.The experimental results show that the proposed model for the constructed dataset achieves high performance and is capable of mining the rich geological information.
基金supported by the Bill & Melinda Gates Foundation and the Minderoo Foundation
文摘Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development.Traditional neural network methods,such as BiLSTM,could be ineffective due to the lack of lab data for model training and the overshadowing of crucial features within sequence concatenation.The current work proposes a less data-consuming model incorporating a pre-trained gene sequence model and a mutual information inference operator.Our methodology utilizes gene alignment and deduplication algorithms to preprocess gene sequences,enhancing the model’s capacity to discern and focus on distinctions among input gene pairs.The model,i.e.,DNA Pretrained Cross-Immunity Protection Inference model(DPCIPI),outperforms state-of-theart(SOTA)models in predicting hemagglutination inhibition titer from influenza viral gene sequences only.Improvement in binary cross-immunity prediction is 1.58%in F1,2.34%in precision,1.57%in recall,and 1.57%in Accuracy.For multilevel cross-immunity improvements,the improvement is 2.12%in F1,3.50%in precision,2.19%in recall,and 2.19%in Accuracy.Our study showcases the potential of pre-trained gene models to improve predictions of antigenic variation and cross-immunity.With expanding gene data and advancements in pre-trained models,this approach promises significant impacts on vaccine development and public health.
基金National Key Research and Development Program of China,Grant/Award Number:2021YFC1910402。
文摘Intelligent sorting is an important prerequisite for the full quantitative consumption and harmless disposal of kitchen waste.The existing object detection method based on an ImageNet pre-trained model is an effective way of sorting.Owing to significant domain gaps between natural images and kitchen waste images,it is difficult to reflect the characteristics of diverse scales and dense distribution in kitchen waste based on an ImageNet pre-trained model,leading to poor generalisation.In this article,the authors propose the first pre-trained model for kitchen waste sorting called KitWaSor,which combines both contrastive learning(CL)and masked image modelling(MIM)through self-supervised learning(SSL).First,to address the issue of diverse scales,the authors propose a mixed masking strategy by introducing an incomplete masking branch based on the original random masking branch.It prevents the complete loss of small-scale objects while avoiding excessive leakage of large-scale object pixels.Second,to address the issue of dense distribution,the authors introduce semantic consistency constraints on the basis of the mixed masking strategy.That is,object semantic reasoning is performed through semantic consistency constraints to compensate for the lack of contextual information.To train KitWaSor,the authors construct the first million-level kitchen waste dataset across seasonal and regional distributions,named KWD-Million.Extensive experiments show that KitWaSor achieves state-of-the-art(SOTA)performance on the two most relevant downstream tasks for kitchen waste sorting(i.e.image classification and object detection),demonstrating the effectiveness of the proposed KitWaSor.
基金supported via funding from Prince Sattam bin Abdulaziz University(PSAU/2025/R/1446)Princess Nourah bint Abdulrahman University(PNURSP2025R300)Prince Sultan University.
文摘Deep neural networks provide accurate results for most applications.However,they need a big dataset to train properly.Providing a big dataset is a significant challenge in most applications.Image augmentation refers to techniques that increase the amount of image data.Common operations for image augmentation include changes in illumination,rotation,contrast,size,viewing angle,and others.Recently,Generative Adversarial Networks(GANs)have been employed for image generation.However,like image augmentation methods,GAN approaches can only generate images that are similar to the original images.Therefore,they also cannot generate new classes of data.Texture images presentmore challenges than general images,and generating textures is more complex than creating other types of images.This study proposes a gradient-based deep neural network method that generates a new class of texture.It is possible to rapidly generate new classes of textures using different kernels from pre-trained deep networks.After generating new textures for each class,the number of textures increases through image augmentation.During this process,several techniques are proposed to automatically remove incomplete and similar textures that are created.The proposed method is faster than some well-known generative networks by around 4 to 10 times.In addition,the quality of the generated textures surpasses that of these networks.The proposed method can generate textures that surpass those of someGANs and parametric models in certain image qualitymetrics.It can provide a big texture dataset to train deep networks.A new big texture dataset is created artificially using the proposed method.This dataset is approximately 2 GB in size and comprises 30,000 textures,each 150×150 pixels in size,organized into 600 classes.It is uploaded to the Kaggle site and Google Drive.This dataset is called BigTex.Compared to other texture datasets,the proposed dataset is the largest and can serve as a comprehensive texture dataset for training more powerful deep neural networks and mitigating overfitting.
文摘We analyze the suitability of existing pre-trained transformer-based language models(PLMs)for abstractive text summarization on German technical healthcare texts.The study focuses on the multilingual capabilities of these models and their ability to perform the task of abstractive text summarization in the healthcare field.The research hypothesis was that large language models could perform high-quality abstractive text summarization on German technical healthcare texts,even if the model is not specifically trained in that language.Through experiments,the research questions explore the performance of transformer language models in dealing with complex syntax constructs,the difference in performance between models trained in English and German,and the impact of translating the source text to English before conducting the summarization.We conducted an evaluation of four PLMs(GPT-3,a translation-based approach also utilizing GPT-3,a German language Model,and a domain-specific bio-medical model approach).The evaluation considered the informativeness using 3 types of metrics based on Recall-Oriented Understudy for Gisting Evaluation(ROUGE)and the quality of results which is manually evaluated considering 5 aspects.The results show that text summarization models could be used in the German healthcare domain and that domain-independent language models achieved the best results.The study proves that text summarization models can simplify the search for pre-existing German knowledge in various domains.
基金supported by the National Natural Science Foundation of China(U1435220)
文摘How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.
基金Supported by the National Natural Science Foundation of China (62006150)Songjiang District Science and Technology Research Project (19SJKJGG83)Shanghai Young Science and Technology Talents Sailing Program (19YF1418400)。
文摘Vision-Language-Navigation(VLN) task is a cross-modality task that combines natural language processing and computer vision. This task requires the agent to automatically move to the destination according to the natural language instruction and the observed surrounding visual information. To make the best decision, in every step during the navigation, the agent should pay more attention to understanding the objects, the object attributes, and the object relationships. But most current methods process all received textual and visual information equally. Therefore, this paper integrates more detailed semantic connections between visual and textual information through three pre-training tasks(object prediction, object attributes prediction, and object relationship prediction). The model will learn better fusion representation and alignment between these two types of information to improve the success rate(SR) and generalization. The experiments show that compared with the former baseline models, the SR on the unseen validation set(Val Unseen) increased by 7%, and the SR weighted by path length(SPL) increased by 7%;the SR on the test set(Test) increased 4%, SPL increased by 3%.
文摘Web-based training is growing quickly in popularit y for professionals in industrial organizations and large enterprises. The savings in cost and time are significant. The instructor-led trainings are bounded by time and place, not to mention the cost involved in traveling, accommodation and training venue. However, in the most online training courses, all trainees are given same training materials and teaching paradigms. The problem of differentia ting the trainees’ abilities is the main concern. We need a pre-training test t o identify and classify of the weaknesses and strengths of differentiate trainee s so as to devise an appropriate training programs for the trainees. Adaptation of a Web-based Computer adaptive Test (CAT) for the pre-training test make the web-based training more efficient. The advantages of CAT are self-pacing, eff iciency, time and cost saving, immediate scoring and feedback, accuracy and secu rity, etc (Rudner, 1998; UMN, 1999; Novell, 2000; Linacre, 2000; Windowsglore, 2 000). Moreover, Web-based CAT also gives greater flexibility and convenience. T his paper describes how this CAT tool is built, how it helps instructor identify the strengths and weaknesses of trainees, and how to assure quality on the CAT system.
文摘Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.
文摘We present an approach to classify medical text at a sentence level automatically.Given the inherent complexity of medical text classification,we employ adapters based on pre-trained language models to extract information from medical text,facilitating more accurate classification while minimizing the number of trainable parameters.Extensive experiments conducted on various datasets demonstrate the effectiveness of our approach.
文摘In multimodal learning, Vision-Language Models (VLMs) have become a critical research focus, enabling the integration of textual and visual data. These models have shown significant promise across various natural language processing tasks, such as visual question answering and computer vision applications, including image captioning and image-text retrieval, highlighting their adaptability for complex, multimodal datasets. In this work, we review the landscape of Bootstrapping Language-Image Pre-training (BLIP) and other VLM techniques. A comparative analysis is conducted to assess VLMs’ strengths, limitations, and applicability across tasks while examining challenges such as scalability, data quality, and fine-tuning complexities. The work concludes by outlining potential future directions in VLM research, focusing on enhancing model interpretability, addressing ethical implications, and advancing multimodal integration in real-world applications.
基金supported by the National Natural Science Foundation of China(Grant No.52078212)the State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin,and China Institute of Water Resources and Hydropower Research,China(No.IWHR-SKL-202003).
文摘Coarse-grained soils are fundamental to major infrastructures like embankments,roads,and bridges.Understanding their deformation characteristics is essential for ensuring structural stability.Traditional methods,such as triaxial compression tests and numerical simulations,face challenges like high costs,time consumption,and limited generalizability across different soils and conditions.To address these limitations,this study employs deep learning to predict the volumetric strain of coarse-grained soils as axial strain changes,aiming to obtain the axial strain(ε_(a))-volumetric strain(ε_(v))curve,which helps derive key mechanical parameters like cohesion(c),and elastic modulus(E).However,the limited data from triaxial tests poses challenges for training deep learning models.We propose using a Time-series Generative Adversarial Network(TimeGAN)for data augmentation.Additionally,we apply feature importance analysis to assess the quality of the numerical augmented data,providing feedback for improving the TimeGAN model.To further enhance model performance,we introduce the pre-training strategy to reduce bias between augmented and real data.Experimental results demonstrate that our approach effectively predictscurve,with the mean absolute error(MAE)of 0.2219 and the R^(2) of 0.9155.The analysis aligns with established findings in soil mechanics,underscoring the potential of our method in engineering applications.
基金funded by the Deanship of Scientific Research at Northern Border University,Arar,Saudi Arabia,through the project number“NBU-FFR-2025-1197-01”.
文摘Cyberbullying is a remarkable issue in the Arabic-speaking world,affecting children,organizations,and businesses.Various efforts have been made to combat this problem through proposed models using machine learning(ML)and deep learning(DL)approaches utilizing natural language processing(NLP)methods and by proposing relevant datasets.However,most of these endeavors focused predominantly on the English language,leaving a substantial gap in addressing Arabic cyberbullying.Given the complexities of the Arabic language,transfer learning techniques and transformers present a promising approach to enhance the detection and classification of abusive content by leveraging large and pretrained models that use a large dataset.Therefore,this study proposes a hybrid model using transformers trained on extensive Arabic datasets.It then fine-tunes the hybrid model on a newly curated Arabic cyberbullying dataset collected from social media platforms,in particular Twitter.Additionally,the following two hybrid transformer models are introduced:the first combines CAmelid Morphologically-aware pretrained Bidirectional Encoder Representations from Transformers(CAMeLBERT)with Arabic Generative Pre-trained Transformer 2(AraGPT2)and the second combines Arabic BERT(AraBERT)with Cross-lingual Language Model-RoBERTa(XLM-R).Two strategies,namely,feature fusion and ensemble voting,are employed to improve the model performance accuracy.Experimental results,measured through precision,recall,F1-score,accuracy,and AreaUnder the Curve-Receiver Operating Characteristic(AUC-ROC),demonstrate that the combined CAMeLBERT and AraGPT2 models using feature fusion outperformed traditional DL models,such as Long Short-Term Memory(LSTM)and Bidirectional Long Short-Term Memory(BiLSTM),as well as other independent Arabic-based transformer models.
基金funded by the National Key Technology R&D Program of China under Grant No.2021YFD2100605the National Natural Science Foundation of China under Grant No.62433002+1 种基金the Project of Construction and Support for High-Level Innovative Teams of Beijing Municipal Institutions under Grant No.BPHR20220104Beijing Scholars Program under Grant No.099.
文摘Entity relation extraction,a fundamental and essential task in natural language processing(NLP),has garnered significant attention over an extended period.,aiming to extract the core of semantic knowledge from unstructured text,i.e.,entities and the relations between them.At present,the main dilemma of Chinese entity relation extraction research lies in nested entities,relation overlap,and lack of entity relation interaction.This dilemma is particularly prominent in complex knowledge extraction tasks with high-density knowledge,imprecise syntactic structure,and lack of semantic roles.To address these challenges,this paper presents an innovative“character-level”Chinese part-of-speech(CN-POS)tagging approach and incorporates part-of-speech(POS)information into the pre-trained model,aiming to improve its semantic understanding and syntactic information processing capabilities.Additionally,A relation reference filling mechanism(RF)is proposed to enhance the semantic interaction between relations and entities,utilize relations to guide entity modeling,improve the boundary prediction ability of entity models for nested entity phenomena,and increase the cascading accuracy of entity-relation triples.Meanwhile,the“Queue”sub-task connection strategy is adopted to alleviate triplet cascading errors caused by overlapping relations,and a Syntax-enhanced entity relation extraction model(SE-RE)is constructed.The model showed excellent performance on the self-constructed E-commerce Product Information dataset(EPI)in this article.The results demonstrate that integrating POS enhancement into the pre-trained encoding model significantly boosts the performance of entity relation extraction models compared to baseline methods.Specifically,the F1-score fluctuation in subtasks caused by error accumulation was reduced by 3.21%,while the F1-score for entity-relation triplet extraction improved by 1.91%.
基金supported by Postgraduate Scientific Research Innovation Project of Hunan Province CX20230915National Natural Science Foundation of China under Grant 62472440.
文摘In the Visual Place Recognition(VPR)task,existing research has leveraged large-scale pre-trained models to improve the performance of place recognition.However,when there are significant environmental differences between query images and reference images,a large number of ineffective local features will interfere with the extraction of key landmark features,leading to the retrieval of visually similar but geographically different images.To address this perceptual aliasing problem caused by environmental condition changes,we propose a novel Visual Place Recognition method with Cross-Environment Robust Feature Enhancement(CerfeVPR).This method uses the GAN network to generate similar images of the original images under different environmental conditions,thereby enhancing the learning of robust features of the original images.This enables the global descriptor to effectively ignore appearance changes caused by environmental factors such as seasons and lighting,showing better place recognition accuracy than other methods.Meanwhile,we introduce a large kernel convolution adapter to fine tune the pre-trained model,obtaining a better image feature representation for subsequent robust feature learning.Then,we process the information of different local regions in the general features through a 3-layer pyramid scene parsing network and fuse it with a tag that retains global information to construct a multi-dimensional image feature representation.Based on this,we use the fused features of similar images to drive the robust feature learning of the original images and complete the feature matching between query images and retrieved images.Experiments on multiple commonly used datasets show that our method exhibits excellent performance.On average,CerfeVPR achieves the highest results,with all Recall@N values exceeding 90%.In particular,on the highly challenging Nordland dataset,the R@1 metric is improved by 4.6%,significantly outperforming other methods,which fully verifies the superiority of CerfeVPR in visual place recognition under complex environments.
基金supported by the Natural Science Foundation of Xinjiang Uygur Autonomous Region under Grant No.2023D01C21the National Natural Science Foundation of China under Grant No.62362063.
文摘Existing image manipulation localization(IML)techniques require large,densely annotated sets of forged images.This requirement greatly increases labeling costs and limits a model’s ability to handle manipulation types that are novel or absent from the training data.To address these issues,we present CLIP-IML,an IML framework that leverages contrastive language-image pre-training(CLIP).A lightweight feature-reconstruction module transforms CLIP token sequences into spatial tensors,after which a compact feature-pyramid network and a multi-scale fusion decoder work together to capture information from fine to coarse levels.We evaluated CLIP-IML on ten public datasets that cover copy-move,splicing,removal,and artificial intelligence(AI)-generated forgeries.The framework raises the average F1-score by 7.85%relative to the strongest recent baselines and secures either the first-or second-place performance on every dataset.Ablation studies show that CLIP pre-training,higher resolution inputs,and the multi-scale decoder each make complementary contributions.Under six common post-processing perturbations,as well as the compression pipelines used by Facebook,Weibo,and WeChat,the performance decline never exceeds 2.2%,confirming strong practical robustness.Moreover,CLIP-IML requires only a few thousand annotated images for training,which markedly reduces data-collection and labeling effort compared with previous methods.All of these results indicate that CLIP-IML is highly generalizable for image tampering localization across a wide range of tampering scenarios.
基金supported by the National Natural Science Foundation of China(No.62376198)the National Key Research and Development Program of China(No.2022YFB3104700)the Shanghai Baiyulan Pujiang Project(No.08002360429).
文摘Early exiting has shown significant potential in accelerating the inference of pre-trained language models(PLMs)by allowing easy samples to exit from shallow layers.However,existing early exiting methods primarily rely on local information from individual samples to estimate prediction uncertainty for making exiting decisions,overlooking the global information provided by the sample population.This impacts the estimation of prediction uncertainty,compromising the reliability of exiting de-cisions.To remedy this,inspired by principal component analysis(PCA),the authors define a residual score to capture the deviation of features from the principal space of the sample population,providing a global perspective for estimating prediction uncertainty.Building on this,a two-stage exiting strategy is proposed that integrates global information from residual scores with local information from energy scores at both the decision and feature levels.This strategy incorporates three-way decisions to enable more reliable exiting decisions for boundary region samples by delaying judgement.Extensive experiments on the GLUE benchmark validate that the method achieves an average speed-up ratio of 2.17×across all tasks with minimal per-formance degradation.Additionally,it surpasses the state-of-the-art E-LANG by 11%in model acceleration,along with a performance improvement of 0.6 points,demonstrating a better performance-efficiency trade-off.
基金funded by the Science and Technology Foundation of Chongqing EducationCommission(GrantNo.KJQN202301153)the ScientificResearch Foundation of Chongqing University of Technology(Grant No.2021ZDZ025)the Postgraduate Innovation Foundation of Chongqing University of Technology(Grant No.gzlcx20243524).
文摘In task-oriented dialogue systems, intent, emotion, and actions are crucial elements of user activity. Analyzing the relationships among these elements to control and manage task-oriented dialogue systems is a challenging task. However, previous work has primarily focused on the independent recognition of user intent and emotion, making it difficult to simultaneously track both aspects in the dialogue tracking module and to effectively utilize user emotions in subsequent dialogue strategies. We propose a Multi-Head Encoder Shared Model (MESM) that dynamically integrates features from emotion and intent encoders through a feature fusioner. Addressing the scarcity of datasets containing both emotion and intent labels, we designed a multi-dataset learning approach enabling the model to generate dialogue summaries encompassing both user intent and emotion. Experiments conducted on the MultiWoZ and MELD datasets demonstrate that our model effectively captures user intent and emotion, achieving extremely competitive results in dialogue state tracking tasks.
