Xuelian Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xuelian Yu has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Haohao Ren
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
12 shared publications - Lin Zou
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
11 shared publications - Xuegang Wang
University of Electronic Science and Technology of China
7 shared publications - Yun Zhou
University of Electronic Science and Technology of China (UESTC)
7 shared publications Xuegang Wang
University of Electronic Science and Technology of China, School of Information and Communication Engineering, Chengdu, China
5 shared publications- Hao Tang
Peking University, Beijing, China
3 shared publications
Latest Publications
- 26 May 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
A frequency-enhanced Mamba network for few-shot SAR ATR
- 26 May 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
A frequency-enhanced Mamba network for few-shot SAR ATR
- Open Access
- 27 August 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17  (17) , 2980
Relation-Guided Embedding Transductive Propagation Network with Residual Correction for Few-Shot SAR ATR
Deep learning-based methods have shown great promise for synthetic aperture radar (SAR) automatic target recognition (ATR) in recent years. These methods demonstrate superior performance compared to traditional approaches across various recognition tasks. However, these methods often face significant challenges due to the limited availability of labeled samples, which is a common issue in SAR image analysis owing to the high cost and difficulty of data annotation. To address this issue, a variety of few-shot learning approaches have been proposed and have demonstrated promising results under data-scarce conditions. Nonetheless, a notable limitation of many existing few-shot methods is that their performance tends to plateau when more labeled samples become available. Most few-shot methods are optimized for scenarios with extremely limited data. As a result, they often fail to leverage the advantages of larger datasets. This leads to suboptimal recognition performance compared to conventional deep learning techniques when sufficient training data is available. Therefore, there is a pressing need for approaches that not only excel in few-shot scenarios but also maintain robust performance as the number of labeled samples increases. To this end, we propose a novel method, termed relation-guided embedding transductive propagation network with residual correction (RGE-TPNRC), specifically designed for few-shot SAR ATR tasks. By leveraging mechanisms such as relation node modeling, relation-guided embedding propagation, and residual correction, RGE-TPNRC can fully utilize limited labeled samples by deeply exploring inter-sample relations, enabling better scalability as the support set size increases. Consequently, it effectively addresses the plateauing performance problem of existing few-shot learning methods when more labeled samples become available. Firstly, input samples are transformed into support-query relation nodes, explicitly capturing the dependencies between support and query samples. Secondly, the known relations among support samples are utilized to guide the propagation of embeddings within the network, enabling manifold smoothing and allowing the model to generalize effectively to unseen target classes. Finally, a residual correction propagation classifier refines predictions by correcting potential errors and smoothing decision boundaries, ensuring robust and accurate classification. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) and OpenSARShip datasets demonstrate that our method can achieve state-of-the-art performance in few-shot SAR ATR scenarios.
- 27 August 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17  (17) , 2980
Open AccessRelation-Guided Embedding Transductive Propagation Network with Residual Correction for Few-Shot SAR ATR
Deep learning-based methods have shown great promise for synthetic aperture radar (SAR) automatic target recognition (ATR) in recent years. These methods demonstrate superior performance compared to traditional approaches across various recognition tasks. However, these methods often face significant challenges due to the limited availability of labeled samples, which is a common issue in SAR image analysis owing to the high cost and difficulty of data annotation. To address this issue, a variety of few-shot learning approaches have been proposed and have demonstrated promising results under data-scarce conditions. Nonetheless, a notable limitation of many existing few-shot methods is that their performance tends to plateau when more labeled samples become available. Most few-shot methods are optimized for scenarios with extremely limited data. As a result, they often fail to leverage the advantages of larger datasets. This leads to suboptimal recognition performance compared to conventional deep learning techniques when sufficient training data is available. Therefore, there is a pressing need for approaches that not only excel in few-shot scenarios but also maintain robust performance as the number of labeled samples increases. To this end, we propose a novel method, termed relation-guided embedding transductive propagation network with residual correction (RGE-TPNRC), specifically designed for few-shot SAR ATR tasks. By leveraging mechanisms such as relation node modeling, relation-guided embedding propagation, and residual correction, RGE-TPNRC can fully utilize limited labeled samples by deeply exploring inter-sample relations, enabling better scalability as the support set size increases. Consequently, it effectively addresses the plateauing performance problem of existing few-shot learning methods when more labeled samples become available. Firstly, input samples are transformed into support-query relation nodes, explicitly capturing the dependencies between support and query samples. Secondly, the known relations among support samples are utilized to guide the propagation of embeddings within the network, enabling manifold smoothing and allowing the model to generalize effectively to unseen target classes. Finally, a residual correction propagation classifier refines predictions by correcting potential errors and smoothing decision boundaries, ensuring robust and accurate classification. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) and OpenSARShip datasets demonstrate that our method can achieve state-of-the-art performance in few-shot SAR ATR scenarios.
- Open Access
- 25 September 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16  (19) , 3563
Enhanced Prototypical Network with Customized Region-Aware Convolution for Few-Shot SAR ATR
With the prosperous development and successful application of deep learning technologies in the field of remote sensing, numerous deep-learning-based methods have emerged for synthetic aperture radar (SAR) automatic target recognition (ATR) tasks over the past few years. Generally, most deep-learning-based methods can achieve outstanding recognition performance on the condition that an abundance of labeled samples are available to train the model. However, in real application scenarios, it is difficult and costly to acquire and to annotate abundant SAR images due to the imaging mechanism of SAR, which poses a big challenge to existing SAR ATR methods. Therefore, SAR target recognition in the situation of few-shot, where only a scarce few labeled samples are available, is a fundamental problem that needs to be solved. In this paper, a new method named enhanced prototypical network with customized region-aware convolution (CRCEPN) is put forward to specially tackle the few-shot SAR ATR tasks. To be specific, a feature-extraction network based on a customized and region-aware convolution is first developed. This network can adaptively adjust convolutional kernels and their receptive fields according to each SAR image’s own characteristics as well as the semantical similarity among spatial regions, thus augmenting its capability to extract more informative and discriminative features. To achieve accurate and robust target identity prediction under the few-shot condition, an enhanced prototypical network is proposed. This network can improve the representation ability of the class prototype by properly making use of training and test samples together, thus effectively raising the classification accuracy. Meanwhile, a new hybrid loss is designed to learn a feature space with both inter-class separability and intra-class tightness as much as possible, which can further upgrade the recognition performance of the proposed method. Experiments performed on the moving and stationary target acquisition and recognition (MSTAR) dataset, the OpenSARShip dataset, and the SAMPLE+ dataset demonstrate that the proposed method is competitive with some state-of-the-art methods for few-shot SAR ATR tasks.
- 25 September 2024
- Published by MDPI AG in Remote Sensing
- Vol. 16  (19) , 3563
Open AccessEnhanced Prototypical Network with Customized Region-Aware Convolution for Few-Shot SAR ATR
With the prosperous development and successful application of deep learning technologies in the field of remote sensing, numerous deep-learning-based methods have emerged for synthetic aperture radar (SAR) automatic target recognition (ATR) tasks over the past few years. Generally, most deep-learning-based methods can achieve outstanding recognition performance on the condition that an abundance of labeled samples are available to train the model. However, in real application scenarios, it is difficult and costly to acquire and to annotate abundant SAR images due to the imaging mechanism of SAR, which poses a big challenge to existing SAR ATR methods. Therefore, SAR target recognition in the situation of few-shot, where only a scarce few labeled samples are available, is a fundamental problem that needs to be solved. In this paper, a new method named enhanced prototypical network with customized region-aware convolution (CRCEPN) is put forward to specially tackle the few-shot SAR ATR tasks. To be specific, a feature-extraction network based on a customized and region-aware convolution is first developed. This network can adaptively adjust convolutional kernels and their receptive fields according to each SAR image’s own characteristics as well as the semantical similarity among spatial regions, thus augmenting its capability to extract more informative and discriminative features. To achieve accurate and robust target identity prediction under the few-shot condition, an enhanced prototypical network is proposed. This network can improve the representation ability of the class prototype by properly making use of training and test samples together, thus effectively raising the classification accuracy. Meanwhile, a new hybrid loss is designed to learn a feature space with both inter-class separability and intra-class tightness as much as possible, which can further upgrade the recognition performance of the proposed method. Experiments performed on the moving and stationary target acquisition and recognition (MSTAR) dataset, the OpenSARShip dataset, and the SAMPLE+ dataset demonstrate that the proposed method is competitive with some state-of-the-art methods for few-shot SAR ATR tasks.
- Open Access
- 29 July 2024
- Published by MDPI AG in Preprints.org
Enhanced Prototypical Network with Customized Region-Aware Convolution for Few-Shot SAR ATR
With prosperous development and successful application of deep learning technologies in the field of remote sensing, numerous deep-learning based methods have emerged for synthetic aperture radar (SAR) automatic target recognition (ATR) tasks over the past few years. Generally, most deep-learning based methods can achieve outstanding recognition performance in condition that an abundant of labeled samples are available to train the model. However, in real application scenarios, it is difficult and costly to acquire and to annotate abundant SAR images due to the imaging mechanism of SAR, which poses a big challenge to existing SAR ATR methods. Thereby, SAR target recognition under the situation of few-shot, where only a scarcely few of labeled samples are available, is a fundamental problem that needs to be solved. In this paper, we put forward a new method named enhanced prototypical network with customized region-aware convolution (CRCEPN) to specially tackle the few-shot SAR ATR tasks. To be specific, We first develop a feature extraction network based on a customized and region-aware convolution, which can adaptively adjust convolutional kernels and their receptive fields according to each SAR image’s own characteristics as well as the semantical similarity among spatial regions, thus augmenting its capability to extract more informative and discriminative features. To achieve accurate and robust target identity prediction under the few-shot condition, we then propose an enhanced prototypical network which can improve the representation ability of the class prototype by properly making use of training and test samples together, thus effectively raising the classification accuracy. Meanwhile, a new hybrid loss is designed to learn a feature space with both inter-class separability and intra-class tightness as much as possible, which can further upgrade the recognition performance of the proposed method. Experiments performed on the moving and stationary target acquisition and recognition (MSTAR) dataset and the OpenSARShip dataset demonstrate that the proposed method is competitive with some state-of-the-art methods for few-shot SAR ATR tasks.
- 29 July 2024
- Published by MDPI AG in Preprints.org
Open AccessEnhanced Prototypical Network with Customized Region-Aware Convolution for Few-Shot SAR ATR
With prosperous development and successful application of deep learning technologies in the field of remote sensing, numerous deep-learning based methods have emerged for synthetic aperture radar (SAR) automatic target recognition (ATR) tasks over the past few years. Generally, most deep-learning based methods can achieve outstanding recognition performance in condition that an abundant of labeled samples are available to train the model. However, in real application scenarios, it is difficult and costly to acquire and to annotate abundant SAR images due to the imaging mechanism of SAR, which poses a big challenge to existing SAR ATR methods. Thereby, SAR target recognition under the situation of few-shot, where only a scarcely few of labeled samples are available, is a fundamental problem that needs to be solved. In this paper, we put forward a new method named enhanced prototypical network with customized region-aware convolution (CRCEPN) to specially tackle the few-shot SAR ATR tasks. To be specific, We first develop a feature extraction network based on a customized and region-aware convolution, which can adaptively adjust convolutional kernels and their receptive fields according to each SAR image’s own characteristics as well as the semantical similarity among spatial regions, thus augmenting its capability to extract more informative and discriminative features. To achieve accurate and robust target identity prediction under the few-shot condition, we then propose an enhanced prototypical network which can improve the representation ability of the class prototype by properly making use of training and test samples together, thus effectively raising the classification accuracy. Meanwhile, a new hybrid loss is designed to learn a feature space with both inter-class separability and intra-class tightness as much as possible, which can further upgrade the recognition performance of the proposed method. Experiments performed on the moving and stationary target acquisition and recognition (MSTAR) dataset and the OpenSARShip dataset demonstrate that the proposed method is competitive with some state-of-the-art methods for few-shot SAR ATR tasks.
- 10 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24  (16) , 26091-26103
Hybrid Reasoning Network With Class-Oriented Hierarchical Representation for Few-Shot SAR Target Recognition
The rise of deep learning has furnished a potent boost for the rapid development of automatic target recognition (ATR) in synthetic aperture radar (SAR) imagery. Existing SAR ATR methods can achieve impressive results with a great many labeled samples available. However, in real SAR application scenarios, the acquisition of quite a few SAR samples is costly or sometimes infeasible. Thus, SAR target recognition under the condition of sample scarcity is a fundamental issue to be overcome urgently. In this paper, we put forward an ATR method named hybrid reasoning network with class-oriented hierarchical representation (HRNCHR) to achieve SAR target recognition with limited training samples. First, we develop a feature extraction model with local-global information concurrent refinement mechanism, which aims to simultaneously refine diverse features at both local and global levels from limited samples. Then, a hierarchical representation space that can learn hierarchical relationships between categories by utilizing diverse features learned from the feature extraction model is established, which is convenient to generalize to few-shot SAR target recognition tasks with the aid of category hierarchical relationship. Finally, a hybrid reasoning strategy is presented, which affords to fuse the reasoning results of instance-level and prototype-level to promote the accuracy of decision-making system. Extensive evaluation experiments on the publicly released moving and stationary target acquisition and recognition (MSTAR) dataset and OpenSARship dataset illustrate that the proposed method surpasses many state-of-the-art SAR ATR methods.
- 10 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24  (16) , 26091-26103
Hybrid Reasoning Network With Class-Oriented Hierarchical Representation for Few-Shot SAR Target Recognition
The rise of deep learning has furnished a potent boost for the rapid development of automatic target recognition (ATR) in synthetic aperture radar (SAR) imagery. Existing SAR ATR methods can achieve impressive results with a great many labeled samples available. However, in real SAR application scenarios, the acquisition of quite a few SAR samples is costly or sometimes infeasible. Thus, SAR target recognition under the condition of sample scarcity is a fundamental issue to be overcome urgently. In this paper, we put forward an ATR method named hybrid reasoning network with class-oriented hierarchical representation (HRNCHR) to achieve SAR target recognition with limited training samples. First, we develop a feature extraction model with local-global information concurrent refinement mechanism, which aims to simultaneously refine diverse features at both local and global levels from limited samples. Then, a hierarchical representation space that can learn hierarchical relationships between categories by utilizing diverse features learned from the feature extraction model is established, which is convenient to generalize to few-shot SAR target recognition tasks with the aid of category hierarchical relationship. Finally, a hybrid reasoning strategy is presented, which affords to fuse the reasoning results of instance-level and prototype-level to promote the accuracy of decision-making system. Extensive evaluation experiments on the publicly released moving and stationary target acquisition and recognition (MSTAR) dataset and OpenSARship dataset illustrate that the proposed method surpasses many state-of-the-art SAR ATR methods.
- 23 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24  (5) , 6700-6708
Threshold-Free Open-Set Learning Network for SAR Automatic Target Recognition
Many advanced automatic target recognition (ATR) methods for synthetic aperture radar (SAR) encounter limitations as they heavily rely on the assumption of a closed-set environment. Consequently, these methods face challenges in effectively identifying and classifying targets from novel categories. Therefore, this paper puts forward an ATR method called threshold-free open-set learning network (TfOsLN) for unknown category detection and known category recognition of SAR targets in an open world. On the basis of generative adversarial network (GAN), the proposed TfOsLN abandons the threshold-based decision-making mechanism, and formulates the open-set problem as a K+1 classification problem. First, to avoid model collapse of the generator, we leverage Kullback–Leibler (KL) divergence to maximize the difference between images synthesized by two random noise inputs with the same label. Then, a dynamic-aware discriminator is proposed to dynamically learn discriminative features according to the target category, thereby enhancing the discrimination between known and unknown categories. Moreover, a multi-task loss is devised to optimize the proposed method, which aims to perform well on unknown categories detection and known categories recognition. Experiments on the moving and stationary target acquisition (MSTAR) and synthetic and measured paired and labeled experiment (SAMPLE) datasets illustrate that the proposed method is superior to some state-of-the-arts for open-set SAR target recognition tasks.
- 23 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24  (5) , 6700-6708
Threshold-Free Open-Set Learning Network for SAR Automatic Target Recognition
Many advanced automatic target recognition (ATR) methods for synthetic aperture radar (SAR) encounter limitations as they heavily rely on the assumption of a closed-set environment. Consequently, these methods face challenges in effectively identifying and classifying targets from novel categories. Therefore, this paper puts forward an ATR method called threshold-free open-set learning network (TfOsLN) for unknown category detection and known category recognition of SAR targets in an open world. On the basis of generative adversarial network (GAN), the proposed TfOsLN abandons the threshold-based decision-making mechanism, and formulates the open-set problem as a K+1 classification problem. First, to avoid model collapse of the generator, we leverage Kullback–Leibler (KL) divergence to maximize the difference between images synthesized by two random noise inputs with the same label. Then, a dynamic-aware discriminator is proposed to dynamically learn discriminative features according to the target category, thereby enhancing the discrimination between known and unknown categories. Moreover, a multi-task loss is devised to optimize the proposed method, which aims to perform well on unknown categories detection and known categories recognition. Experiments on the moving and stationary target acquisition (MSTAR) and synthetic and measured paired and labeled experiment (SAMPLE) datasets illustrate that the proposed method is superior to some state-of-the-arts for open-set SAR target recognition tasks.
- 11 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21  (1545598X) , 1-5
Dynamic Embedding Relation Distillation Network for Incremental SAR Automatic Target Recognition
In realistic synthetic aperture radar (SAR) scenarios, new categories of targets continue to appear over time. It requires the automatic target recognition (ATR) model should continue to accommodate and recognize new categories of targets while maintaining stability on old categories of targets. Therefore, how to strike a glorious balance between plasticity and stability is a matter of wide concern for incremental SAR ATR. In this letter, we propose a new incremental ATR method called dynamic embedding relation distillation network (DERDN), which strives to alleviate the dilemma between plasticity and stability. Specifically, we first develop a dynamic feature embedding model whose parameters can be adjusted adaptively with the data, which is very conducive to continuous generalization to new category targets. To mitigate catastrophic forgetting of the model on old categories, we then propose a relation distillation strategy based on exemplar replay to recall knowledge of old categories, thereby improving the stability of the model. Moreover, a hybrid loss that takes into account both label space and embedding space is presented, which ensures interclass discriminability while enhancing intraclass compactness in the feature space, so as to sustainably accommodate new categories. Evaluation experiments on two benchmark datasets, i.e., moving and stationary target acquisition and recognition (MSTAR) and the synthetic and measured paired labeled experiment (SAMPLE), illustrate that the proposed method is competitive with many state of the arts. The recognition rate of the proposed method is up to 3% higher than that of the best competitor, and its forgetting rate is about 2.5% lower than that of the best competitor.
- 11 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21  (1545598X) , 1-5
Dynamic Embedding Relation Distillation Network for Incremental SAR Automatic Target Recognition
In realistic synthetic aperture radar (SAR) scenarios, new categories of targets continue to appear over time. It requires the automatic target recognition (ATR) model should continue to accommodate and recognize new categories of targets while maintaining stability on old categories of targets. Therefore, how to strike a glorious balance between plasticity and stability is a matter of wide concern for incremental SAR ATR. In this letter, we propose a new incremental ATR method called dynamic embedding relation distillation network (DERDN), which strives to alleviate the dilemma between plasticity and stability. Specifically, we first develop a dynamic feature embedding model whose parameters can be adjusted adaptively with the data, which is very conducive to continuous generalization to new category targets. To mitigate catastrophic forgetting of the model on old categories, we then propose a relation distillation strategy based on exemplar replay to recall knowledge of old categories, thereby improving the stability of the model. Moreover, a hybrid loss that takes into account both label space and embedding space is presented, which ensures interclass discriminability while enhancing intraclass compactness in the feature space, so as to sustainably accommodate new categories. Evaluation experiments on two benchmark datasets, i.e., moving and stationary target acquisition and recognition (MSTAR) and the synthetic and measured paired labeled experiment (SAMPLE), illustrate that the proposed method is competitive with many state of the arts. The recognition rate of the proposed method is up to 3% higher than that of the best competitor, and its forgetting rate is about 2.5% lower than that of the best competitor.
- 23 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61  (01962892) , 1-13
Adaptive Convolutional Subspace Reasoning Network for Few-Shot SAR Target Recognition
Data-driven automatic target recognition (ATR) methods have become the mainstream in the synthetic aperture radar (SAR) community at this stage. However, in real SAR application scenarios, the scarcity of training samples is a common problem. Especially in military application scenarios, only a small number of samples of each type of target are usually available. In the case of limited available samples, it is bound to bring challenges to the feature extraction model and classifier inference learning. In this paper, we propose a novel method called adaptive convolutional subspace reasoning network (ACSRNet) to address few-shot SAR target recognition tasks. To be specific, we first present a dynamic-aware convolutional feature embedding network based on the siamese architecture, which can not only learn more transferable knowledge for the few-shot tasks, but also dynamically adjust the convolution kernel according to the input data to extract more discriminative features. To effectively achieve target identity reasoning, we then resort to high-order information of samples, i.e., the idea of adaptive subspace learning, to develop a few-shot subspace classification module, which can online reason the identity of the unknown target through the spanning subspace of training samples. Meanwhile, a dual-loss is designed to train a feature embedding space with intra-class compactness and inter-class divergence, aiming to facilitate subsequent classification. Meta-learning integrating random sampling episode way is introduced into the process of model training to realize few-shot SAR ATR tasks by emulating the human cognitive process. Experimental results on the moving and stationary target acquisition recognition (MSTAR) dataset demonstrate that the proposed method is competitive with some state-of-the-arts for few-shot SAR ATR tasks.
- 23 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61  (01962892) , 1-13
Adaptive Convolutional Subspace Reasoning Network for Few-Shot SAR Target Recognition
Data-driven automatic target recognition (ATR) methods have become the mainstream in the synthetic aperture radar (SAR) community at this stage. However, in real SAR application scenarios, the scarcity of training samples is a common problem. Especially in military application scenarios, only a small number of samples of each type of target are usually available. In the case of limited available samples, it is bound to bring challenges to the feature extraction model and classifier inference learning. In this paper, we propose a novel method called adaptive convolutional subspace reasoning network (ACSRNet) to address few-shot SAR target recognition tasks. To be specific, we first present a dynamic-aware convolutional feature embedding network based on the siamese architecture, which can not only learn more transferable knowledge for the few-shot tasks, but also dynamically adjust the convolution kernel according to the input data to extract more discriminative features. To effectively achieve target identity reasoning, we then resort to high-order information of samples, i.e., the idea of adaptive subspace learning, to develop a few-shot subspace classification module, which can online reason the identity of the unknown target through the spanning subspace of training samples. Meanwhile, a dual-loss is designed to train a feature embedding space with intra-class compactness and inter-class divergence, aiming to facilitate subsequent classification. Meta-learning integrating random sampling episode way is introduced into the process of model training to realize few-shot SAR ATR tasks by emulating the human cognitive process. Experimental results on the moving and stationary target acquisition recognition (MSTAR) dataset demonstrate that the proposed method is competitive with some state-of-the-arts for few-shot SAR ATR tasks.
- 28 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61  (01962892) , 1-13
Transductive Prototypical Attention Reasoning Network for Few-Shot SAR Target Recognition
Deep learning-based synthetic aperture radar (SAR) automatic target recognition (ATR) algorithms have achieved outstanding performance under the condition of hundreds or thousands of training samples in recent years. Nevertheless, it is often rare to acquire great quantities of target samples in real SAR application scenarios. This article proposes a novel ATR method called transductive prototypical attention reasoning network (TPARN) to solve the problem of SAR target recognition with only a few training samples. To be specific, a region awareness-based feature extraction model is first developed, which can effectively focus on the target region of interest and suppress the background clutter by embedding direction-aware and position-sensitive information to extract more transferable knowledge. To heighten the discrimination of the sample features, a cross-feature spatial attention module is then proposed following the feature embedding model. Finally, a transductive prototype reasoning method is presented to realize the identity reasoning of the target, which can continuously update each class prototype with training samples and test samples together, thereby improving the classification accuracy. In addition, a marginal adaptive hybrid loss is proposed to obtain a discriminative feature embedding space with intra-class compactness and inter-class divergence, aiming to facilitate subsequent target identity reasoning. Extensive experiments on the moving and stationary target acquisition and recognition (MSTAR) benchmark dataset reveal that the proposed method outperforms some state-of-the-arts under different few-shot SAR ATR tasks.
- 28 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61  (01962892) , 1-13
Transductive Prototypical Attention Reasoning Network for Few-Shot SAR Target Recognition
Deep learning-based synthetic aperture radar (SAR) automatic target recognition (ATR) algorithms have achieved outstanding performance under the condition of hundreds or thousands of training samples in recent years. Nevertheless, it is often rare to acquire great quantities of target samples in real SAR application scenarios. This article proposes a novel ATR method called transductive prototypical attention reasoning network (TPARN) to solve the problem of SAR target recognition with only a few training samples. To be specific, a region awareness-based feature extraction model is first developed, which can effectively focus on the target region of interest and suppress the background clutter by embedding direction-aware and position-sensitive information to extract more transferable knowledge. To heighten the discrimination of the sample features, a cross-feature spatial attention module is then proposed following the feature embedding model. Finally, a transductive prototype reasoning method is presented to realize the identity reasoning of the target, which can continuously update each class prototype with training samples and test samples together, thereby improving the classification accuracy. In addition, a marginal adaptive hybrid loss is proposed to obtain a discriminative feature embedding space with intra-class compactness and inter-class divergence, aiming to facilitate subsequent target identity reasoning. Extensive experiments on the moving and stationary target acquisition and recognition (MSTAR) benchmark dataset reveal that the proposed method outperforms some state-of-the-arts under different few-shot SAR ATR tasks.
- 31 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20  (1545598X) , 1-5
Multilevel Adaptive Knowledge Distillation Network for Incremental SAR Target Recognition
The existing synthetic aperture radar (SAR) automatic target recognition (ATR) methods have shown impressive results in static scenarios, yet the performance drops sharply as new categories of targets are continuously increased. In response to this problem, this letter proposes a novel ATR method named multi-level adaptive knowledge distillation network (MLAKDN) to achieve incremental SAR target recognition. To be specific, an adaptive weighted distillation strategy is first proposed, which can alleviate the model from forgetting the knowledge of old categories by distilling multi-stage soft label information of old categories at the classification level. Then, a feature distillation method based on gradient maximum criterion is developed to filter and distill discriminative features, so as to further recall more knowledge of old categories at the feature level. Meanwhile, a model rebalancing technique is designed to effectively strike the balance of the model on new categories and old categories. Finally, a weighted incremental classification loss is presented to train the whole model. Experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset and the synthetic and measured paired labeled experiment (SAMPLE) dataset illustrate that the proposed method is superior to some state-of-the-arts for incremental SAR target recognition tasks.
- 31 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20  (1545598X) , 1-5
Multilevel Adaptive Knowledge Distillation Network for Incremental SAR Target Recognition
The existing synthetic aperture radar (SAR) automatic target recognition (ATR) methods have shown impressive results in static scenarios, yet the performance drops sharply as new categories of targets are continuously increased. In response to this problem, this letter proposes a novel ATR method named multi-level adaptive knowledge distillation network (MLAKDN) to achieve incremental SAR target recognition. To be specific, an adaptive weighted distillation strategy is first proposed, which can alleviate the model from forgetting the knowledge of old categories by distilling multi-stage soft label information of old categories at the classification level. Then, a feature distillation method based on gradient maximum criterion is developed to filter and distill discriminative features, so as to further recall more knowledge of old categories at the feature level. Meanwhile, a model rebalancing technique is designed to effectively strike the balance of the model on new categories and old categories. Finally, a weighted incremental classification loss is presented to train the whole model. Experiments on the moving and stationary target acquisition and recognition (MSTAR) dataset and the synthetic and measured paired labeled experiment (SAMPLE) dataset illustrate that the proposed method is superior to some state-of-the-arts for incremental SAR target recognition tasks.