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
Named entity recognition(NER)in musk deer domain is the extraction of specific types of entities from unstructured texts,constituting a fundamental component of the knowledge graph,Q&A system,and text summarizatio...Named entity recognition(NER)in musk deer domain is the extraction of specific types of entities from unstructured texts,constituting a fundamental component of the knowledge graph,Q&A system,and text summarization system of musk deer domain.Due to limited annotated data,diverse entity types,and the ambiguity of Chinese word boundaries in musk deer domain NER,we present a novel NER model,CAELF-GP,which is based on cross-attention mechanism enhanced lexical features(CAELF).Specifically,we employ BERT as a character encoder and advocate the integration of external lexical information at the character representation layer.In the feature fusion module,instead of indiscriminately merging external dictionary information,we innovatively adopted a feature fusion method based on a cross-attention mechanism,which guides the model to focus on important lexical information by calculating the correlation between each character and its corresponding word sets.This module enhances the model’s semantic representation ability and entity boundary recognition capability.Ultimately,we introduce the decoding module of GlobalPointer(GP)for entity type recognition,capable of identifying both nested and non-nested entities.Since there is currently no publicly available dataset for the musk deer domain,we built a named entity recognition dataset for this domain by collecting relevant literature and working under the guidance of domain experts.The dataset facilitates the training and validation of the model and provides data foundation for subsequent related research.The model undergoes experimentation on two public datasets and the dataset of musk deer domain.The results show that it is superior to the baseline models,offering a promising technical avenue for the intelligent recognition of named entities in the musk deer domain.展开更多
Tibetan medical named entity recognition(Tibetan MNER)involves extracting specific types of medical entities from unstructured Tibetan medical texts.Tibetan MNER provide important data support for the work related to ...Tibetan medical named entity recognition(Tibetan MNER)involves extracting specific types of medical entities from unstructured Tibetan medical texts.Tibetan MNER provide important data support for the work related to Tibetan medicine.However,existing Tibetan MNER methods often struggle to comprehensively capture multi-level semantic information,failing to sufficiently extract multi-granularity features and effectively filter out irrelevant information,which ultimately impacts the accuracy of entity recognition.This paper proposes an improved embedding representation method called syllable-word-sentence embedding.By leveraging features at different granularities and using un-scaled dot-product attention to focus on key features for feature fusion,the syllable-word-sentence embedding is integrated into the transformer,enhancing the specificity and diversity of feature representations.The model leverages multi-level and multi-granularity semantic information,thereby improving the performance of Tibetan MNER.We evaluate our proposed model on datasets from various domains.The results indicate that the model effectively identified three types of entities in the Tibetan news dataset we constructed,achieving an F1 score of 93.59%,which represents an improvement of 1.24%compared to the vanilla FLAT.Additionally,results from the Tibetan medical dataset we developed show that it is effective in identifying five kinds of medical entities,with an F1 score of 71.39%,which is a 1.34%improvement over the vanilla FLAT.展开更多
Named Entity Recognition(NER)is vital in natural language processing for the analysis of news texts,as it accurately identifies entities such as locations,persons,and organizations,which is crucial for applications li...Named Entity Recognition(NER)is vital in natural language processing for the analysis of news texts,as it accurately identifies entities such as locations,persons,and organizations,which is crucial for applications like news summarization and event tracking.However,NER in the news domain faces challenges due to insufficient annotated data,complex entity structures,and strong context dependencies.To address these issues,we propose a new Chinesenamed entity recognition method that integrates transfer learning with word embeddings.Our approach leverages the ERNIE pre-trained model for transfer learning and obtaining general language representations and incorporates the Soft-lexicon word embedding technique to handle varied entity structures.This dual-strategy enhances the model’s understanding of context and boosts its ability to process complex texts.Experimental results show that our method achieves an F1 score of 94.72% on a news dataset,surpassing baseline methods by 3%–4%,thereby confirming its effectiveness for Chinese-named entity recognition in the news domain.展开更多
Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or ...Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or obtaining entity related external knowledge from knowledge bases or Large Language Models(LLMs).However,these approaches ignore the poor semantic correlation between visual and textual modalities in MNER datasets and do not explore different multi-modal fusion approaches.In this paper,we present MMAVK,a multi-modal named entity recognition model with auxiliary visual knowledge and word-level fusion,which aims to leverage the Multi-modal Large Language Model(MLLM)as an implicit knowledge base.It also extracts vision-based auxiliary knowledge from the image formore accurate and effective recognition.Specifically,we propose vision-based auxiliary knowledge generation,which guides the MLLM to extract external knowledge exclusively derived from images to aid entity recognition by designing target-specific prompts,thus avoiding redundant recognition and cognitive confusion caused by the simultaneous processing of image-text pairs.Furthermore,we employ a word-level multi-modal fusion mechanism to fuse the extracted external knowledge with each word-embedding embedded from the transformerbased encoder.Extensive experimental results demonstrate that MMAVK outperforms or equals the state-of-the-art methods on the two classical MNER datasets,even when the largemodels employed have significantly fewer parameters than other baselines.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
Named Entity Recognition(NER)stands as a fundamental task within the field of biomedical text mining,aiming to extract specific types of entities such as genes,proteins,and diseases from complex biomedical texts and c...Named Entity Recognition(NER)stands as a fundamental task within the field of biomedical text mining,aiming to extract specific types of entities such as genes,proteins,and diseases from complex biomedical texts and categorize them into predefined entity types.This process can provide basic support for the automatic construction of knowledge bases.In contrast to general texts,biomedical texts frequently contain numerous nested entities and local dependencies among these entities,presenting significant challenges to prevailing NER models.To address these issues,we propose a novel Chinese nested biomedical NER model based on RoBERTa and Global Pointer(RoBGP).Our model initially utilizes the RoBERTa-wwm-ext-large pretrained language model to dynamically generate word-level initial vectors.It then incorporates a Bidirectional Long Short-Term Memory network for capturing bidirectional semantic information,effectively addressing the issue of long-distance dependencies.Furthermore,the Global Pointer model is employed to comprehensively recognize all nested entities in the text.We conduct extensive experiments on the Chinese medical dataset CMeEE and the results demonstrate the superior performance of RoBGP over several baseline models.This research confirms the effectiveness of RoBGP in Chinese biomedical NER,providing reliable technical support for biomedical information extraction and knowledge base construction.展开更多
Geological reports are a significant accomplishment for geologists involved in geological investigations and scientific research as they contain rich data and textual information.With the rapid development of science ...Geological reports are a significant accomplishment for geologists involved in geological investigations and scientific research as they contain rich data and textual information.With the rapid development of science and technology,a large number of textual reports have accumulated in the field of geology.However,many non-hot topics and non-English speaking regions are neglected in mainstream geoscience databases for geological information mining,making it more challenging for some researchers to extract necessary information from these texts.Natural Language Processing(NLP)has obvious advantages in processing large amounts of textual data.The objective of this paper is to identify geological named entities from Chinese geological texts using NLP techniques.We propose the RoBERTa-Prompt-Tuning-NER method,which leverages the concept of Prompt Learning and requires only a small amount of annotated data to train superior models for recognizing geological named entities in low-resource dataset configurations.The RoBERTa layer captures context-based information and longer-distance dependencies through dynamic word vectors.Finally,we conducted experiments on the constructed Geological Named Entity Recognition(GNER)dataset.Our experimental results show that the proposed model achieves the highest F1 score of 80.64%among the four baseline algorithms,demonstrating the reliability and robustness of using the model for Named Entity Recognition of geological texts.展开更多
Named entity recognition(NER)is an important part in knowledge extraction and one of the main tasks in constructing knowledge graphs.In today’s Chinese named entity recognition(CNER)task,the BERT-BiLSTM-CRF model is ...Named entity recognition(NER)is an important part in knowledge extraction and one of the main tasks in constructing knowledge graphs.In today’s Chinese named entity recognition(CNER)task,the BERT-BiLSTM-CRF model is widely used and often yields notable results.However,recognizing each entity with high accuracy remains challenging.Many entities do not appear as single words but as part of complex phrases,making it difficult to achieve accurate recognition using word embedding information alone because the intricate lexical structure often impacts the performance.To address this issue,we propose an improved Bidirectional Encoder Representations from Transformers(BERT)character word conditional random field(CRF)(BCWC)model.It incorporates a pre-trained word embedding model using the skip-gram with negative sampling(SGNS)method,alongside traditional BERT embeddings.By comparing datasets with different word segmentation tools,we obtain enhanced word embedding features for segmented data.These features are then processed using the multi-scale convolution and iterated dilated convolutional neural networks(IDCNNs)with varying expansion rates to capture features at multiple scales and extract diverse contextual information.Additionally,a multi-attention mechanism is employed to fuse word and character embeddings.Finally,CRFs are applied to learn sequence constraints and optimize entity label annotations.A series of experiments are conducted on three public datasets,demonstrating that the proposed method outperforms the recent advanced baselines.BCWC is capable to address the challenge of recognizing complex entities by combining character-level and word-level embedding information,thereby improving the accuracy of CNER.Such a model is potential to the applications of more precise knowledge extraction such as knowledge graph construction and information retrieval,particularly in domain-specific natural language processing tasks that require high entity recognition precision.展开更多
Fine-grained aircraft target detection in remote sensing holds significant research valueand practical applications,particularly in military defense and precision strikes.Given the complex-ity of remote sensing images...Fine-grained aircraft target detection in remote sensing holds significant research valueand practical applications,particularly in military defense and precision strikes.Given the complex-ity of remote sensing images,where targets are often small and similar within categories,detectingthese fine-grained targets is challenging.To address this,we constructed a fine-grained dataset ofremotely sensed airplanes;for the problems of remote sensing fine-grained targets with obvious head-to-tail distributions and large variations in target sizes,we proposed the DWDet fine-grained tar-get detection and recognition algorithm.First,for the problem of unbalanced category distribution,we adopt an adaptive sampling strategy.In addition,we construct a deformable convolutional blockand improve the decoupling head structure to improve the detection effect of the model ondeformed targets.Then,we design a localization loss function,which is used to improve the model’slocalization ability for targets of different scales.The experimental results show that our algorithmimproves the overall accuracy of the model by 4.1%compared to the baseline model,and improvesthe detection accuracy of small targets by 12.2%.The ablation and comparison experiments alsoprove the effectiveness of our algorithm.展开更多
Named entity recognition(NER)is a fundamental task of information extraction(IE),and it has attracted considerable research attention in recent years.The abundant annotated English NER datasets have significantly prom...Named entity recognition(NER)is a fundamental task of information extraction(IE),and it has attracted considerable research attention in recent years.The abundant annotated English NER datasets have significantly promoted the NER research in the English field.By contrast,much fewer efforts are made to the Chinese NER research,especially in the scientific domain,due to the scarcity of Chinese NER datasets.To alleviate this problem,we present aChinese scientificNER dataset–SciCN,which contains entity annotations of titles and abstracts derived from 3,500 scientific papers.We manually annotate a total of 62,059 entities,and these entities are classified into six types.Compared to English scientific NER datasets,SciCN has a larger scale and is more diverse,for it not only contains more paper abstracts but these abstracts are derived from more research fields.To investigate the properties of SciCN and provide baselines for future research,we adapt a number of previous state-of-theart Chinese NER models to evaluate SciCN.Experimental results show that SciCN is more challenging than other Chinese NER datasets.In addition,previous studies have proven the effectiveness of using lexicons to enhance Chinese NER models.Motivated by this fact,we provide a scientific domain-specific lexicon.Validation results demonstrate that our lexicon delivers better performance gains than lexicons of other domains.We hope that the SciCN dataset and the lexicon will enable us to benchmark the NER task regarding the Chinese scientific domain and make progress for future research.The dataset and lexicon are available at:https://github.com/yangjingla/SciCN.git.展开更多
The few-shot named entity recognition(NER)task aims to train a robust model in the source domain and transfer it to the target domain with very few annotated data.Currently,some approaches rely on the prototypical net...The few-shot named entity recognition(NER)task aims to train a robust model in the source domain and transfer it to the target domain with very few annotated data.Currently,some approaches rely on the prototypical network for NER.However,these approaches often overlook the spatial relations in the span boundary matrix because entity words tend to depend more on adjacent words.We propose using a multidimensional convolution module to address this limitation to capture short-distance spatial dependencies.Additionally,we uti-lize an improved prototypical network and assign different weights to different samples that belong to the same class,thereby enhancing the performance of the few-shot NER task.Further experimental analysis demonstrates that our approach has significantly improved over baseline models across multiple datasets.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
Chinese named entity recognition(CNER)has received widespread attention as an important task of Chinese information extraction.Most previous research has focused on individually studying flat CNER,overlapped CNER,or d...Chinese named entity recognition(CNER)has received widespread attention as an important task of Chinese information extraction.Most previous research has focused on individually studying flat CNER,overlapped CNER,or discontinuous CNER.However,a unified CNER is often needed in real-world scenarios.Recent studies have shown that grid tagging-based methods based on character-pair relationship classification hold great potential for achieving unified NER.Nevertheless,how to enrich Chinese character-pair grid representations and capture deeper dependencies between character pairs to improve entity recognition performance remains an unresolved challenge.In this study,we enhance the character-pair grid representation by incorporating both local and global information.Significantly,we introduce a new approach by considering the character-pair grid representation matrix as a specialized image,converting the classification of character-pair relationships into a pixel-level semantic segmentation task.We devise a U-shaped network to extract multi-scale and deeper semantic information from the grid image,allowing for a more comprehensive understanding of associative features between character pairs.This approach leads to improved accuracy in predicting their relationships,ultimately enhancing entity recognition performance.We conducted experiments on two public CNER datasets in the biomedical domain,namely CMeEE-V2 and Diakg.The results demonstrate the effectiveness of our approach,which achieves F1-score improvements of 7.29 percentage points and 1.64 percentage points compared to the current state-of-the-art(SOTA)models,respectively.展开更多
Assembly process documents record the designers'intention or knowledge.However,common knowl-edge extraction methods are not well suitable for assembly process documents,because of its tabular form and unstructured...Assembly process documents record the designers'intention or knowledge.However,common knowl-edge extraction methods are not well suitable for assembly process documents,because of its tabular form and unstructured natural language texts.In this paper,an assembly semantic entity recognition and relation con-struction method oriented to assembly process documents is proposed.First,the assembly process sentences are extracted from the table through concerned region recognition and cell division,and they will be stored as a key-value object file.Then,the semantic entities in the sentence are identified through the sequence tagging model based on the specific attention mechanism for assembly operation type.The syntactic rules are designed for realizing automatic construction of relation between entities.Finally,by using the self-constructed corpus,it is proved that the sequence tagging model in the proposed method performs better than the mainstream named entity recognition model when handling assembly process design language.The effectiveness of the proposed method is also analyzed through the simulation experiment in the small-scale real scene,compared with manual method.The results show that the proposed method can help designers accumulate knowledge automatically and efficiently.展开更多
Mathematical named entity recognition(MNER)is one of the fundamental tasks in the analysis of mathematical texts.To solve the existing problems of the current neural network that has local instability,fuzzy entity bou...Mathematical named entity recognition(MNER)is one of the fundamental tasks in the analysis of mathematical texts.To solve the existing problems of the current neural network that has local instability,fuzzy entity boundary,and long-distance dependence between entities in Chinese mathematical entity recognition task,we propose a series of optimization processing methods and constructed an Adversarial Training and Bidirectional long shortterm memory-Selfattention Conditional random field(AT-BSAC)model.In our model,the mathematical text was vectorized by the word embedding technique,and small perturbations were added to the word vector to generate adversarial samples,while local features were extracted by Bi-directional Long Short-Term Memory(BiLSTM).The self-attentive mechanism was incorporated to extract more dependent features between entities.The experimental results demonstrated that the AT-BSAC model achieved a precision(P)of 93.88%,a recall(R)of 93.84%,and an F1-score of 93.74%,respectively,which is 8.73%higher than the F1-score of the previous Bi-directional Long Short-Term Memory Conditional Random Field(BiLSTM-CRF)model.The effectiveness of the proposed model in mathematical named entity recognition.展开更多
Automatic extraction of key data from design specifications is an important means to assist in engineering design automation.Considering the characteristics of diverse data types,small scale,insufficient character inf...Automatic extraction of key data from design specifications is an important means to assist in engineering design automation.Considering the characteristics of diverse data types,small scale,insufficient character information content and strong contextual relevance of design specification,a named entity recognition model integrated with high-quality topic and attention mechanism,namely Quality Topic-Char Embedding-BiLSTMAttention-CRF,was proposed to automatically identify entities in design specification.Based on the topic model,an improved algorithm for high-quality topic extraction was proposed first,and then the high-quality topic information obtained was added into the distributed representation of Chinese characters to better enrich character features.Next,the attention mechanism was used in parallel on the basis of the BiLSTM-CRF model to fully mine the contextual semantic information.Finally,the experiment was performed on the collected corpus of Chinese ship design specification,and the model was compared with multiple sets of models.The results show that F-score(harmonic mean of precision and recall)of the model is 80.24%.The model performs better than other models in design specification,and is expected to provide an automatic means for engineering design.展开更多
Named Entity Recognition(NER)is crucial for extracting structured information from text.While traditional methods rely on rules,Conditional Random Fields(CRFs),or deep learning,the advent of large-scale Pre-trained La...Named Entity Recognition(NER)is crucial for extracting structured information from text.While traditional methods rely on rules,Conditional Random Fields(CRFs),or deep learning,the advent of large-scale Pre-trained Language Models(PLMs)offers new possibilities.PLMs excel at contextual learning,potentially simplifying many natural language processing tasks.However,their application to NER remains underexplored.This paper investigates leveraging the GPT-3 PLM for NER without fine-tuning.We propose a novel scheme that utilizes carefully crafted templates and context examples selected based on semantic similarity.Our experimental results demonstrate the feasibility of this approach,suggesting a promising direction for harnessing PLMs in NER.展开更多
Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal windo...Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal window to learn local video representation.However,these methods failed to capture complex motion patterns due to their limited receptive field.To solve the above problems,this paper proposes a lightweight Temporal Pyramid Excitation(TPE)module to capture the short,medium,and long-term temporal context.In this method,Temporal Pyramid(TP)module can effectively expand the temporal receptive field of the network by using the multi-temporal kernel decomposition without significantly increasing the computational cost.In addition,the Multi Excitation module can emphasize temporal importance to enhance the temporal feature representation learning.TPE can be integrated into ResNet50,and building a compact video learning framework-TPENet.Extensive validation experiments on several challenging benchmark(Something-Something V1,Something-Something V2,UCF-101,and HMDB51)datasets demonstrate that our method achieves a preferable balance between computation and accuracy.展开更多
The fine-grained ship image recognition task aims to identify various classes of ships.However,small inter-class,large intra-class differences between ships,and lacking of training samples are the reasons that make th...The fine-grained ship image recognition task aims to identify various classes of ships.However,small inter-class,large intra-class differences between ships,and lacking of training samples are the reasons that make the task difficult.Therefore,to enhance the accuracy of the fine-grained ship image recognition,we design a fine-grained ship image recognition network based on bilinear convolutional neural network(BCNN)with Inception and additive margin Softmax(AM-Softmax).This network improves the BCNN in two aspects.Firstly,by introducing Inception branches to the BCNN network,it is helpful to enhance the ability of extracting comprehensive features from ships.Secondly,by adding margin values to the decision boundary,the AM-Softmax function can better extend the inter-class differences and reduce the intra-class differences.In addition,as there are few publicly available datasets for fine-grained ship image recognition,we construct a Ship-43 dataset containing 47,300 ship images belonging to 43 categories.Experimental results on the constructed Ship-43 dataset demonstrate that our method can effectively improve the accuracy of ship image recognition,which is 4.08%higher than the BCNN model.Moreover,comparison results on the other three public fine-grained datasets(Cub,Cars,and Aircraft)further validate the effectiveness of the proposed method.展开更多
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funded by 5·5 Engineering Research&Innovation Team Project of Beijing Forestry University(No.BLRC2023C02).
文摘Named entity recognition(NER)in musk deer domain is the extraction of specific types of entities from unstructured texts,constituting a fundamental component of the knowledge graph,Q&A system,and text summarization system of musk deer domain.Due to limited annotated data,diverse entity types,and the ambiguity of Chinese word boundaries in musk deer domain NER,we present a novel NER model,CAELF-GP,which is based on cross-attention mechanism enhanced lexical features(CAELF).Specifically,we employ BERT as a character encoder and advocate the integration of external lexical information at the character representation layer.In the feature fusion module,instead of indiscriminately merging external dictionary information,we innovatively adopted a feature fusion method based on a cross-attention mechanism,which guides the model to focus on important lexical information by calculating the correlation between each character and its corresponding word sets.This module enhances the model’s semantic representation ability and entity boundary recognition capability.Ultimately,we introduce the decoding module of GlobalPointer(GP)for entity type recognition,capable of identifying both nested and non-nested entities.Since there is currently no publicly available dataset for the musk deer domain,we built a named entity recognition dataset for this domain by collecting relevant literature and working under the guidance of domain experts.The dataset facilitates the training and validation of the model and provides data foundation for subsequent related research.The model undergoes experimentation on two public datasets and the dataset of musk deer domain.The results show that it is superior to the baseline models,offering a promising technical avenue for the intelligent recognition of named entities in the musk deer domain.
基金supported in part by the National Science and Technology Major Project under(Grant 2022ZD0116100)in part by the National Natural Science Foundation Key Project under(Grant 62436006)+4 种基金in part by the National Natural Science Foundation Youth Fund under(Grant 62406257)in part by the Xizang Autonomous Region Natural Science Foundation General Project under(Grant XZ202401ZR0031)in part by the National Natural Science Foundation of China under(Grant 62276055)in part by the Sichuan Science and Technology Program under(Grant 23ZDYF0755)in part by the Xizang University‘High-Level Talent Training Program’Project under(Grant 2022-GSP-S098).
文摘Tibetan medical named entity recognition(Tibetan MNER)involves extracting specific types of medical entities from unstructured Tibetan medical texts.Tibetan MNER provide important data support for the work related to Tibetan medicine.However,existing Tibetan MNER methods often struggle to comprehensively capture multi-level semantic information,failing to sufficiently extract multi-granularity features and effectively filter out irrelevant information,which ultimately impacts the accuracy of entity recognition.This paper proposes an improved embedding representation method called syllable-word-sentence embedding.By leveraging features at different granularities and using un-scaled dot-product attention to focus on key features for feature fusion,the syllable-word-sentence embedding is integrated into the transformer,enhancing the specificity and diversity of feature representations.The model leverages multi-level and multi-granularity semantic information,thereby improving the performance of Tibetan MNER.We evaluate our proposed model on datasets from various domains.The results indicate that the model effectively identified three types of entities in the Tibetan news dataset we constructed,achieving an F1 score of 93.59%,which represents an improvement of 1.24%compared to the vanilla FLAT.Additionally,results from the Tibetan medical dataset we developed show that it is effective in identifying five kinds of medical entities,with an F1 score of 71.39%,which is a 1.34%improvement over the vanilla FLAT.
基金funded by Advanced Research Project(30209040702).
文摘Named Entity Recognition(NER)is vital in natural language processing for the analysis of news texts,as it accurately identifies entities such as locations,persons,and organizations,which is crucial for applications like news summarization and event tracking.However,NER in the news domain faces challenges due to insufficient annotated data,complex entity structures,and strong context dependencies.To address these issues,we propose a new Chinesenamed entity recognition method that integrates transfer learning with word embeddings.Our approach leverages the ERNIE pre-trained model for transfer learning and obtaining general language representations and incorporates the Soft-lexicon word embedding technique to handle varied entity structures.This dual-strategy enhances the model’s understanding of context and boosts its ability to process complex texts.Experimental results show that our method achieves an F1 score of 94.72% on a news dataset,surpassing baseline methods by 3%–4%,thereby confirming its effectiveness for Chinese-named entity recognition in the news domain.
基金funded by Research Project,grant number BHQ090003000X03.
文摘Multi-modal Named Entity Recognition(MNER)aims to better identify meaningful textual entities by integrating information from images.Previous work has focused on extracting visual semantics at a fine-grained level,or obtaining entity related external knowledge from knowledge bases or Large Language Models(LLMs).However,these approaches ignore the poor semantic correlation between visual and textual modalities in MNER datasets and do not explore different multi-modal fusion approaches.In this paper,we present MMAVK,a multi-modal named entity recognition model with auxiliary visual knowledge and word-level fusion,which aims to leverage the Multi-modal Large Language Model(MLLM)as an implicit knowledge base.It also extracts vision-based auxiliary knowledge from the image formore accurate and effective recognition.Specifically,we propose vision-based auxiliary knowledge generation,which guides the MLLM to extract external knowledge exclusively derived from images to aid entity recognition by designing target-specific prompts,thus avoiding redundant recognition and cognitive confusion caused by the simultaneous processing of image-text pairs.Furthermore,we employ a word-level multi-modal fusion mechanism to fuse the extracted external knowledge with each word-embedding embedded from the transformerbased encoder.Extensive experimental results demonstrate that MMAVK outperforms or equals the state-of-the-art methods on the two classical MNER datasets,even when the largemodels employed have significantly fewer parameters than other baselines.
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.
基金supported by the Outstanding Youth Team Project of Central Universities(QNTD202308)the Ant Group through CCF-Ant Research Fund(CCF-AFSG 769498 RF20220214).
文摘Named Entity Recognition(NER)stands as a fundamental task within the field of biomedical text mining,aiming to extract specific types of entities such as genes,proteins,and diseases from complex biomedical texts and categorize them into predefined entity types.This process can provide basic support for the automatic construction of knowledge bases.In contrast to general texts,biomedical texts frequently contain numerous nested entities and local dependencies among these entities,presenting significant challenges to prevailing NER models.To address these issues,we propose a novel Chinese nested biomedical NER model based on RoBERTa and Global Pointer(RoBGP).Our model initially utilizes the RoBERTa-wwm-ext-large pretrained language model to dynamically generate word-level initial vectors.It then incorporates a Bidirectional Long Short-Term Memory network for capturing bidirectional semantic information,effectively addressing the issue of long-distance dependencies.Furthermore,the Global Pointer model is employed to comprehensively recognize all nested entities in the text.We conduct extensive experiments on the Chinese medical dataset CMeEE and the results demonstrate the superior performance of RoBGP over several baseline models.This research confirms the effectiveness of RoBGP in Chinese biomedical NER,providing reliable technical support for biomedical information extraction and knowledge base construction.
基金supported by the National Natural Science Foundation of China(Nos.42488201,42172137,42050104,and 42050102)the National Key R&D Program of China(No.2023YFF0804000)Sichuan Provincial Youth Science&Technology Innovative Research Group Fund(No.2022JDTD0004)
文摘Geological reports are a significant accomplishment for geologists involved in geological investigations and scientific research as they contain rich data and textual information.With the rapid development of science and technology,a large number of textual reports have accumulated in the field of geology.However,many non-hot topics and non-English speaking regions are neglected in mainstream geoscience databases for geological information mining,making it more challenging for some researchers to extract necessary information from these texts.Natural Language Processing(NLP)has obvious advantages in processing large amounts of textual data.The objective of this paper is to identify geological named entities from Chinese geological texts using NLP techniques.We propose the RoBERTa-Prompt-Tuning-NER method,which leverages the concept of Prompt Learning and requires only a small amount of annotated data to train superior models for recognizing geological named entities in low-resource dataset configurations.The RoBERTa layer captures context-based information and longer-distance dependencies through dynamic word vectors.Finally,we conducted experiments on the constructed Geological Named Entity Recognition(GNER)dataset.Our experimental results show that the proposed model achieves the highest F1 score of 80.64%among the four baseline algorithms,demonstrating the reliability and robustness of using the model for Named Entity Recognition of geological texts.
基金supported by the International Research Center of Big Data for Sustainable Development Goals under Grant No.CBAS2022GSP05the Open Fund of State Key Laboratory of Remote Sensing Science under Grant No.6142A01210404the Hubei Key Laboratory of Intelligent Geo-Information Processing under Grant No.KLIGIP-2022-B03.
文摘Named entity recognition(NER)is an important part in knowledge extraction and one of the main tasks in constructing knowledge graphs.In today’s Chinese named entity recognition(CNER)task,the BERT-BiLSTM-CRF model is widely used and often yields notable results.However,recognizing each entity with high accuracy remains challenging.Many entities do not appear as single words but as part of complex phrases,making it difficult to achieve accurate recognition using word embedding information alone because the intricate lexical structure often impacts the performance.To address this issue,we propose an improved Bidirectional Encoder Representations from Transformers(BERT)character word conditional random field(CRF)(BCWC)model.It incorporates a pre-trained word embedding model using the skip-gram with negative sampling(SGNS)method,alongside traditional BERT embeddings.By comparing datasets with different word segmentation tools,we obtain enhanced word embedding features for segmented data.These features are then processed using the multi-scale convolution and iterated dilated convolutional neural networks(IDCNNs)with varying expansion rates to capture features at multiple scales and extract diverse contextual information.Additionally,a multi-attention mechanism is employed to fuse word and character embeddings.Finally,CRFs are applied to learn sequence constraints and optimize entity label annotations.A series of experiments are conducted on three public datasets,demonstrating that the proposed method outperforms the recent advanced baselines.BCWC is capable to address the challenge of recognizing complex entities by combining character-level and word-level embedding information,thereby improving the accuracy of CNER.Such a model is potential to the applications of more precise knowledge extraction such as knowledge graph construction and information retrieval,particularly in domain-specific natural language processing tasks that require high entity recognition precision.
基金supported by National Natural Science Foundation of China(No.62471034)Hebei Natural Science Foundation(No.F2023105001).
文摘Fine-grained aircraft target detection in remote sensing holds significant research valueand practical applications,particularly in military defense and precision strikes.Given the complex-ity of remote sensing images,where targets are often small and similar within categories,detectingthese fine-grained targets is challenging.To address this,we constructed a fine-grained dataset ofremotely sensed airplanes;for the problems of remote sensing fine-grained targets with obvious head-to-tail distributions and large variations in target sizes,we proposed the DWDet fine-grained tar-get detection and recognition algorithm.First,for the problem of unbalanced category distribution,we adopt an adaptive sampling strategy.In addition,we construct a deformable convolutional blockand improve the decoupling head structure to improve the detection effect of the model ondeformed targets.Then,we design a localization loss function,which is used to improve the model’slocalization ability for targets of different scales.The experimental results show that our algorithmimproves the overall accuracy of the model by 4.1%compared to the baseline model,and improvesthe detection accuracy of small targets by 12.2%.The ablation and comparison experiments alsoprove the effectiveness of our algorithm.
基金This research was supported by the National Key Research and Development Program[2020YFB1006302].
文摘Named entity recognition(NER)is a fundamental task of information extraction(IE),and it has attracted considerable research attention in recent years.The abundant annotated English NER datasets have significantly promoted the NER research in the English field.By contrast,much fewer efforts are made to the Chinese NER research,especially in the scientific domain,due to the scarcity of Chinese NER datasets.To alleviate this problem,we present aChinese scientificNER dataset–SciCN,which contains entity annotations of titles and abstracts derived from 3,500 scientific papers.We manually annotate a total of 62,059 entities,and these entities are classified into six types.Compared to English scientific NER datasets,SciCN has a larger scale and is more diverse,for it not only contains more paper abstracts but these abstracts are derived from more research fields.To investigate the properties of SciCN and provide baselines for future research,we adapt a number of previous state-of-theart Chinese NER models to evaluate SciCN.Experimental results show that SciCN is more challenging than other Chinese NER datasets.In addition,previous studies have proven the effectiveness of using lexicons to enhance Chinese NER models.Motivated by this fact,we provide a scientific domain-specific lexicon.Validation results demonstrate that our lexicon delivers better performance gains than lexicons of other domains.We hope that the SciCN dataset and the lexicon will enable us to benchmark the NER task regarding the Chinese scientific domain and make progress for future research.The dataset and lexicon are available at:https://github.com/yangjingla/SciCN.git.
基金Supported by the Scientific and Technological Innovation 2030-Major Project of New Generation Artificial Intelligence(2020AAA0109300)Science and Technology Commission of Shanghai Municipality(21DZ2203100)2023 Anhui Province Key Research and Development Plan Project-Special Project of Science and Technology Cooperation(2023i11020002)。
文摘The few-shot named entity recognition(NER)task aims to train a robust model in the source domain and transfer it to the target domain with very few annotated data.Currently,some approaches rely on the prototypical network for NER.However,these approaches often overlook the spatial relations in the span boundary matrix because entity words tend to depend more on adjacent words.We propose using a multidimensional convolution module to address this limitation to capture short-distance spatial dependencies.Additionally,we uti-lize an improved prototypical network and assign different weights to different samples that belong to the same class,thereby enhancing the performance of the few-shot NER task.Further experimental analysis demonstrates that our approach has significantly improved over baseline models across multiple datasets.
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 Yunnan Provincial Major Science and Technology Special Plan Projects(Grant Nos.202202AD080003,202202AE090008,202202AD080004,202302AD080003)National Natural Science Foundation of China(Grant Nos.U21B2027,62266027,62266028,62266025)Yunnan Province Young and Middle-Aged Academic and Technical Leaders Reserve Talent Program(Grant No.202305AC160063).
文摘Chinese named entity recognition(CNER)has received widespread attention as an important task of Chinese information extraction.Most previous research has focused on individually studying flat CNER,overlapped CNER,or discontinuous CNER.However,a unified CNER is often needed in real-world scenarios.Recent studies have shown that grid tagging-based methods based on character-pair relationship classification hold great potential for achieving unified NER.Nevertheless,how to enrich Chinese character-pair grid representations and capture deeper dependencies between character pairs to improve entity recognition performance remains an unresolved challenge.In this study,we enhance the character-pair grid representation by incorporating both local and global information.Significantly,we introduce a new approach by considering the character-pair grid representation matrix as a specialized image,converting the classification of character-pair relationships into a pixel-level semantic segmentation task.We devise a U-shaped network to extract multi-scale and deeper semantic information from the grid image,allowing for a more comprehensive understanding of associative features between character pairs.This approach leads to improved accuracy in predicting their relationships,ultimately enhancing entity recognition performance.We conducted experiments on two public CNER datasets in the biomedical domain,namely CMeEE-V2 and Diakg.The results demonstrate the effectiveness of our approach,which achieves F1-score improvements of 7.29 percentage points and 1.64 percentage points compared to the current state-of-the-art(SOTA)models,respectively.
文摘Assembly process documents record the designers'intention or knowledge.However,common knowl-edge extraction methods are not well suitable for assembly process documents,because of its tabular form and unstructured natural language texts.In this paper,an assembly semantic entity recognition and relation con-struction method oriented to assembly process documents is proposed.First,the assembly process sentences are extracted from the table through concerned region recognition and cell division,and they will be stored as a key-value object file.Then,the semantic entities in the sentence are identified through the sequence tagging model based on the specific attention mechanism for assembly operation type.The syntactic rules are designed for realizing automatic construction of relation between entities.Finally,by using the self-constructed corpus,it is proved that the sequence tagging model in the proposed method performs better than the mainstream named entity recognition model when handling assembly process design language.The effectiveness of the proposed method is also analyzed through the simulation experiment in the small-scale real scene,compared with manual method.The results show that the proposed method can help designers accumulate knowledge automatically and efficiently.
文摘Mathematical named entity recognition(MNER)is one of the fundamental tasks in the analysis of mathematical texts.To solve the existing problems of the current neural network that has local instability,fuzzy entity boundary,and long-distance dependence between entities in Chinese mathematical entity recognition task,we propose a series of optimization processing methods and constructed an Adversarial Training and Bidirectional long shortterm memory-Selfattention Conditional random field(AT-BSAC)model.In our model,the mathematical text was vectorized by the word embedding technique,and small perturbations were added to the word vector to generate adversarial samples,while local features were extracted by Bi-directional Long Short-Term Memory(BiLSTM).The self-attentive mechanism was incorporated to extract more dependent features between entities.The experimental results demonstrated that the AT-BSAC model achieved a precision(P)of 93.88%,a recall(R)of 93.84%,and an F1-score of 93.74%,respectively,which is 8.73%higher than the F1-score of the previous Bi-directional Long Short-Term Memory Conditional Random Field(BiLSTM-CRF)model.The effectiveness of the proposed model in mathematical named entity recognition.
基金the High Tech Ship Project of the Ministry of Industry and Information Technology(No.[2019]331)。
文摘Automatic extraction of key data from design specifications is an important means to assist in engineering design automation.Considering the characteristics of diverse data types,small scale,insufficient character information content and strong contextual relevance of design specification,a named entity recognition model integrated with high-quality topic and attention mechanism,namely Quality Topic-Char Embedding-BiLSTMAttention-CRF,was proposed to automatically identify entities in design specification.Based on the topic model,an improved algorithm for high-quality topic extraction was proposed first,and then the high-quality topic information obtained was added into the distributed representation of Chinese characters to better enrich character features.Next,the attention mechanism was used in parallel on the basis of the BiLSTM-CRF model to fully mine the contextual semantic information.Finally,the experiment was performed on the collected corpus of Chinese ship design specification,and the model was compared with multiple sets of models.The results show that F-score(harmonic mean of precision and recall)of the model is 80.24%.The model performs better than other models in design specification,and is expected to provide an automatic means for engineering design.
文摘Named Entity Recognition(NER)is crucial for extracting structured information from text.While traditional methods rely on rules,Conditional Random Fields(CRFs),or deep learning,the advent of large-scale Pre-trained Language Models(PLMs)offers new possibilities.PLMs excel at contextual learning,potentially simplifying many natural language processing tasks.However,their application to NER remains underexplored.This paper investigates leveraging the GPT-3 PLM for NER without fine-tuning.We propose a novel scheme that utilizes carefully crafted templates and context examples selected based on semantic similarity.Our experimental results demonstrate the feasibility of this approach,suggesting a promising direction for harnessing PLMs in NER.
基金supported by the research team of Xi’an Traffic Engineering Institute and the Young and middle-aged fund project of Xi’an Traffic Engineering Institute (2022KY-02).
文摘Mining more discriminative temporal features to enrich temporal context representation is considered the key to fine-grained action recog-nition.Previous action recognition methods utilize a fixed spatiotemporal window to learn local video representation.However,these methods failed to capture complex motion patterns due to their limited receptive field.To solve the above problems,this paper proposes a lightweight Temporal Pyramid Excitation(TPE)module to capture the short,medium,and long-term temporal context.In this method,Temporal Pyramid(TP)module can effectively expand the temporal receptive field of the network by using the multi-temporal kernel decomposition without significantly increasing the computational cost.In addition,the Multi Excitation module can emphasize temporal importance to enhance the temporal feature representation learning.TPE can be integrated into ResNet50,and building a compact video learning framework-TPENet.Extensive validation experiments on several challenging benchmark(Something-Something V1,Something-Something V2,UCF-101,and HMDB51)datasets demonstrate that our method achieves a preferable balance between computation and accuracy.
基金This work is supported by the National Natural Science Foundation of China(61806013,61876010,62176009,and 61906005)General project of Science and Technology Planof Beijing Municipal Education Commission(KM202110005028)+2 种基金Beijing Municipal Education Commission Project(KZ201910005008)Project of Interdisciplinary Research Institute of Beijing University of Technology(2021020101)International Research Cooperation Seed Fund of Beijing University of Technology(2021A01).
文摘The fine-grained ship image recognition task aims to identify various classes of ships.However,small inter-class,large intra-class differences between ships,and lacking of training samples are the reasons that make the task difficult.Therefore,to enhance the accuracy of the fine-grained ship image recognition,we design a fine-grained ship image recognition network based on bilinear convolutional neural network(BCNN)with Inception and additive margin Softmax(AM-Softmax).This network improves the BCNN in two aspects.Firstly,by introducing Inception branches to the BCNN network,it is helpful to enhance the ability of extracting comprehensive features from ships.Secondly,by adding margin values to the decision boundary,the AM-Softmax function can better extend the inter-class differences and reduce the intra-class differences.In addition,as there are few publicly available datasets for fine-grained ship image recognition,we construct a Ship-43 dataset containing 47,300 ship images belonging to 43 categories.Experimental results on the constructed Ship-43 dataset demonstrate that our method can effectively improve the accuracy of ship image recognition,which is 4.08%higher than the BCNN model.Moreover,comparison results on the other three public fine-grained datasets(Cub,Cars,and Aircraft)further validate the effectiveness of the proposed method.
