Ke Wang
Research Subjects
Ke Wang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Qi Qiao
Faculty of Computer and Communication, Jiangsu Vocational College of Electronics and Information, Huaian, China
5 shared publications - Huiying Hu
Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Shah Alam, Malaysia
3 shared publications - Azlin Ahmad
Universiti Teknologi MARA
2 shared publications Gong Zhang
Key Laboratory of Radar Imaging and Microwave Photonics, Ministry of Education, Nanjing University of Aeronautics and Astronautics, Nanjing 211100, China
2 shared publications- Henry Leung
University of Calgary, Canada
2 shared publications Yuqian Mao
China State Shipbuilding Corporation Limited
2 shared publications
Latest Publications
- 24 August 2026
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 47 (22) , 10228-10258
A causal semantic intervention framework for few-shot SAR-ATR
1. Synthetic aperture radar (SAR) is an active microwave imaging system capable of acquiring high-resolution observations of ground and maritime targets under all-weather and day-and-night conditio...
- 24 August 2026
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 47 (22) , 10228-10258
A causal semantic intervention framework for few-shot SAR-ATR
1. Synthetic aperture radar (SAR) is an active microwave imaging system capable of acquiring high-resolution observations of ground and maritime targets under all-weather and day-and-night conditio...
- Open Access
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 185726-185740
MSDC-FRN: Multi-Scale Dense Feature Reconstruction for Few-Shot Metal Surface Classification
Automated surface defect classification plays a pivotal role in industrial quality control. However, its efficacy is often constrained by the scarcity of annotated samples in real-world scenarios. This few-shot learning challenge is particularly challenging for metal surfaces, which are characterized by high intra-class variance and subtle inter-class differences among defect types. To address these issues, we propose a novel multi-scale densely connected feature reconstruction network (MSDC-FRN). Our model integrates a multi-scale dense connection backbone to extract rich and robust features across diverse receptive fields. In addition, we introduce a feature reconstruction network (FRN) classifier that measures the sample similarity by framing it as a ridge regression problem. This unique formulation markedly enhances feature discriminability and model generalization. Extensive experiments on two benchmark metal defect datasets demonstrate that MSDC-FRN achieves a performance that is superior or comparable to state-of-the-art methods in both intra-domain and challenging cross-domain settings. These results validate the effectiveness of our model and highlight its potential as a robust solution for intelligent quality inspection in modern manufacturing.
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 185726-185740
Open AccessMSDC-FRN: Multi-Scale Dense Feature Reconstruction for Few-Shot Metal Surface Classification
Automated surface defect classification plays a pivotal role in industrial quality control. However, its efficacy is often constrained by the scarcity of annotated samples in real-world scenarios. This few-shot learning challenge is particularly challenging for metal surfaces, which are characterized by high intra-class variance and subtle inter-class differences among defect types. To address these issues, we propose a novel multi-scale densely connected feature reconstruction network (MSDC-FRN). Our model integrates a multi-scale dense connection backbone to extract rich and robust features across diverse receptive fields. In addition, we introduce a feature reconstruction network (FRN) classifier that measures the sample similarity by framing it as a ridge regression problem. This unique formulation markedly enhances feature discriminability and model generalization. Extensive experiments on two benchmark metal defect datasets demonstrate that MSDC-FRN achieves a performance that is superior or comparable to state-of-the-art methods in both intra-domain and challenging cross-domain settings. These results validate the effectiveness of our model and highlight its potential as a robust solution for intelligent quality inspection in modern manufacturing.
- Open Access
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 181154-181179
A Systematic Literature Review on Few-Shot Image Classification
Few-shot image classification (FSIC) is a critical task in computer vision that aims to accurately classify new categories with only a limited number of labeled examples. This capability is essential for practical applications such as medical diagnosis, remote sensing, and autonomous driving, where data scarcity is common. Although numerous FSIC methods have been proposed, a comprehensive systematic literature review (SLR) remains absent. This review begins by summarizing foundational FSIC approaches and evaluating their effectiveness across standard benchmarks. It then explores recent advancements from 2019 to 2025, providing an in-depth analysis of key factors affecting FSIC performance, including dataset characteristics, model architecture, and evaluation protocols. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, multiple academic databases were searched, resulting in the selection of 26 relevant studies based on strict inclusion and exclusion criteria. The findings highlight that FSIC performance is strongly influenced by factors such as the number of support samples, domain shifts, label noise, and model complexity. Finally, the review identifies future research directions, emphasizing the integration of domain adaptation, lightweight model design, and multimodal learning, while addressing current challenges to guide the next phase of FSIC development.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 181154-181179
Open AccessA Systematic Literature Review on Few-Shot Image Classification
Few-shot image classification (FSIC) is a critical task in computer vision that aims to accurately classify new categories with only a limited number of labeled examples. This capability is essential for practical applications such as medical diagnosis, remote sensing, and autonomous driving, where data scarcity is common. Although numerous FSIC methods have been proposed, a comprehensive systematic literature review (SLR) remains absent. This review begins by summarizing foundational FSIC approaches and evaluating their effectiveness across standard benchmarks. It then explores recent advancements from 2019 to 2025, providing an in-depth analysis of key factors affecting FSIC performance, including dataset characteristics, model architecture, and evaluation protocols. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, multiple academic databases were searched, resulting in the selection of 26 relevant studies based on strict inclusion and exclusion criteria. The findings highlight that FSIC performance is strongly influenced by factors such as the number of support samples, domain shifts, label noise, and model complexity. Finally, the review identifies future research directions, emphasizing the integration of domain adaptation, lightweight model design, and multimodal learning, while addressing current challenges to guide the next phase of FSIC development.
- Open Access
- 15 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 124988-125002
Few-Shot SAR Target Recognition via Causal Inference and Deep Metric Learning
Deep learning, with large-scale annotated datasets, has demonstrated remarkable success in synthetic aperture radar automatic target recognition (SAR-ATR). However, the collecting of SAR images is expensive and complex, and manually labeling them requires expert knowledge. To overcome these limitations, we propose a few-shot learning model capable of accurate recognition of novel targets with minimal training samples. Our model innovatively integrates causal inference with mutual centralized learning (MCL) to address few-shot SAR-ATR tasks. First, we establish a causal inference framework to identify and model the dependencies among target characteristics, imaging conditions, and category labels. This framework incorporates a novel causal intervention method based on multi-scale random convolution to eliminate spurious correlations caused by imaging variations, thereby enhancing feature stability. Second, we introduce an advanced MCL module to effectively evaluate feature similarity in few-shot settings. MCL breaks through the unidirectional matching paradigm adopted by conventional metric learning. Through its bidirectional feature interactions and dense feature accessibility mechanisms, MCL achieves more robust feature discrimination in few-shot learning tasks. Comprehensive experiments demonstrate that our model outperforms existing advanced few-shot SAR-ATR methods, achieving superior recognition accuracy while maintaining robustness in data-scarce scenarios.
- 15 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 124988-125002
Open AccessFew-Shot SAR Target Recognition via Causal Inference and Deep Metric Learning
Deep learning, with large-scale annotated datasets, has demonstrated remarkable success in synthetic aperture radar automatic target recognition (SAR-ATR). However, the collecting of SAR images is expensive and complex, and manually labeling them requires expert knowledge. To overcome these limitations, we propose a few-shot learning model capable of accurate recognition of novel targets with minimal training samples. Our model innovatively integrates causal inference with mutual centralized learning (MCL) to address few-shot SAR-ATR tasks. First, we establish a causal inference framework to identify and model the dependencies among target characteristics, imaging conditions, and category labels. This framework incorporates a novel causal intervention method based on multi-scale random convolution to eliminate spurious correlations caused by imaging variations, thereby enhancing feature stability. Second, we introduce an advanced MCL module to effectively evaluate feature similarity in few-shot settings. MCL breaks through the unidirectional matching paradigm adopted by conventional metric learning. Through its bidirectional feature interactions and dense feature accessibility mechanisms, MCL achieves more robust feature discrimination in few-shot learning tasks. Comprehensive experiments demonstrate that our model outperforms existing advanced few-shot SAR-ATR methods, achieving superior recognition accuracy while maintaining robustness in data-scarce scenarios.
- 3 June 2025
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 46 (12) , 4629-4653
Few-shot SAR target recognition based on deep causal metric learning
- 3 June 2025
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 46 (12) , 4629-4653
Few-shot SAR target recognition based on deep causal metric learning
- Top Cited PapersOpen Access
- 21 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 48380-48400
A Review of Metal Surface Defect Detection Technologies in Industrial Applications
Surface defects, including cracks, scratches, and deformations, significantly affect the product performance and service life in industrial manufacturing. Accurate detection of metal surface defects ensures product quality and reliability. Traditional nondestructive testing (NDT) methods, such as ultrasonic and eddy current inspections, are effective but face challenges in terms of efficiency and scalability for industrial applications. This review examines the recent advancements in automated defect detection, focusing on image acquisition, image processing, and detection techniques. The study also evaluates state-of-the-art machine learning and deep learning methods used in defect detection, including the symmetric convolutional network (SCN), swin transformer you only look once (ST-YOLO), and statistical texture feature enhancement network (STFE-Net), which achieve high accuracy in defect classification and detection. In addition, advanced three-dimensional (3D) detection methods such as photometric stereo, light-field imaging, and structured light have been explored for their potential to address challenges such as real-time detection, few-shot detection, and small-target detection. The study concludes by identifying current limitations and proposing future directions for enhancing industrial defect detection systems.
- 21 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 48380-48400
Top Cited PapersOpen AccessA Review of Metal Surface Defect Detection Technologies in Industrial Applications
Surface defects, including cracks, scratches, and deformations, significantly affect the product performance and service life in industrial manufacturing. Accurate detection of metal surface defects ensures product quality and reliability. Traditional nondestructive testing (NDT) methods, such as ultrasonic and eddy current inspections, are effective but face challenges in terms of efficiency and scalability for industrial applications. This review examines the recent advancements in automated defect detection, focusing on image acquisition, image processing, and detection techniques. The study also evaluates state-of-the-art machine learning and deep learning methods used in defect detection, including the symmetric convolutional network (SCN), swin transformer you only look once (ST-YOLO), and statistical texture feature enhancement network (STFE-Net), which achieve high accuracy in defect classification and detection. In addition, advanced three-dimensional (3D) detection methods such as photometric stereo, light-field imaging, and structured light have been explored for their potential to address challenges such as real-time detection, few-shot detection, and small-target detection. The study concludes by identifying current limitations and proposing future directions for enhancing industrial defect detection systems.
- Open Access
- 1 August 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 35 (2) , 933-943
Image classification based on few-shot learning algorithms: a review
Image classification is a critical task in the field of computer vision, and its importance has significantly increased over the past few years. Machine learning and deep learning techniques have demonstrated immense potential in this field. However, traditional image classification models require a vast amount of training data, which can be challenging and expensive to obtain. To overcome this limitation, researchers are turning to few-shot learning, which aims to classify images with limited training samples. This paper presents a detailed analysis of the field of image classification using few-shot learning. First, it investigates the use of data augmentation, transfer learning, and meta-learning methods in this field. Then, it introduces several commonly used datasets and evaluation metrics in few-shot classification, compares several classical few-shot classification methods, and summarizes the experimental results obtained from public datasets. Finally, this paper analyzes the current challenges in few-shot image classification and suggests potential future directions.
- 1 August 2024
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 35 (2) , 933-943
Open AccessImage classification based on few-shot learning algorithms: a review
Image classification is a critical task in the field of computer vision, and its importance has significantly increased over the past few years. Machine learning and deep learning techniques have demonstrated immense potential in this field. However, traditional image classification models require a vast amount of training data, which can be challenging and expensive to obtain. To overcome this limitation, researchers are turning to few-shot learning, which aims to classify images with limited training samples. This paper presents a detailed analysis of the field of image classification using few-shot learning. First, it investigates the use of data augmentation, transfer learning, and meta-learning methods in this field. Then, it introduces several commonly used datasets and evaluation metrics in few-shot classification, compares several classical few-shot classification methods, and summarizes the experimental results obtained from public datasets. Finally, this paper analyzes the current challenges in few-shot image classification and suggests potential future directions.
- 10 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 18 (4) , 682-686
SAR Target Recognition Based on Probabilistic Meta-Learning
Numerous synthetic aperture radar-automatic target recognition (SAR-ATR) methods require a large amount of training data. However, collecting SAR data is both expensive and complicated in practical applications. Recognition with the limited training data has become a vital issue in SAR-ATR. To solve this problem, we propose a recognition model combining probabilistic inference with meta-learning to transfer prior knowledge from simulated to real SAR data. First, we use various recognition tasks drawn from the simulated data to learn the global parameters of the model. Second, we draw new tasks from the real data and use the amortized inference to model a posterior distribution over task-specific parameters. Finally, we produce a predictive distribution indicating the confidence of the target classes. The experimental results demonstrate the superiority of the model in recognition tasks with a small amount of training data. We also show that introducing probabilistic inference can improve the prediction accuracy and prediction uncertainty of the model.
- 10 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 18 (4) , 682-686
SAR Target Recognition Based on Probabilistic Meta-Learning
Numerous synthetic aperture radar-automatic target recognition (SAR-ATR) methods require a large amount of training data. However, collecting SAR data is both expensive and complicated in practical applications. Recognition with the limited training data has become a vital issue in SAR-ATR. To solve this problem, we propose a recognition model combining probabilistic inference with meta-learning to transfer prior knowledge from simulated to real SAR data. First, we use various recognition tasks drawn from the simulated data to learn the global parameters of the model. Second, we draw new tasks from the real data and use the amortized inference to model a posterior distribution over task-specific parameters. Finally, we produce a predictive distribution indicating the confidence of the target classes. The experimental results demonstrate the superiority of the model in recognition tasks with a small amount of training data. We also show that introducing probabilistic inference can improve the prediction accuracy and prediction uncertainty of the model.
- Open Access
- 21 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 153391-153399
SAR Target Recognition Based on Cross-Domain and Cross-Task Transfer Learning
Inspired by their tremendous success in optical image detection and classification, convolutional neural networks (CNNs) have recently been used in synthetic aperture radar automatic target recognition (SAR-ATR). Although CNN-based methods can achieve excellent recognition performance, it is difficult to collect a large number of real SAR images available for training. In this paper, we introduce simulated SAR data to alleviate the problem of insufficient training data. To address domain shift and task transfer problems caused by differences between simulated and real data, we propose a model that integrates meta-learning and adversarial domain adaptation. We use sufficient simulated data and a few real data to pretrain the model. After fine-tuning, the pre-trained model can quickly adapt to new tasks in real data. Extensive experimental results obtained in the real SAR dataset demonstrate that our model effectively solves the crossdomain and cross-task transfer problem. Compared with conventional SAR-ATR methods, the proposed model can achieve better recognition performance with a small amount of training data.
- 21 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 153391-153399
Open AccessSAR Target Recognition Based on Cross-Domain and Cross-Task Transfer Learning
Inspired by their tremendous success in optical image detection and classification, convolutional neural networks (CNNs) have recently been used in synthetic aperture radar automatic target recognition (SAR-ATR). Although CNN-based methods can achieve excellent recognition performance, it is difficult to collect a large number of real SAR images available for training. In this paper, we introduce simulated SAR data to alleviate the problem of insufficient training data. To address domain shift and task transfer problems caused by differences between simulated and real data, we propose a model that integrates meta-learning and adversarial domain adaptation. We use sufficient simulated data and a few real data to pretrain the model. After fine-tuning, the pre-trained model can quickly adapt to new tasks in real data. Extensive experimental results obtained in the real SAR dataset demonstrate that our model effectively solves the crossdomain and cross-task transfer problem. Compared with conventional SAR-ATR methods, the proposed model can achieve better recognition performance with a small amount of training data.
- 18 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 16 (6) , 912-916
Synthetic Aperture Radar Image Generation With Deep Generative Models
A variety of machine learning approaches have been applied to synthetic aperture radar (SAR) automatic target recognition. The performances of these approaches rely strongly on the quality and quantity of training data. In real-world applications, however, it is challenging to obtain sufficient data suitable for these approaches. To alleviate this problem, a novel deep generative model for SAR image generation is proposed, which is an extension of Wasserstein autoencoder. The network structure and reconstruction loss function of the model have been improved according to the characteristics of SAR images. The experimental results demonstrate that our model is superior to other classical generative models in SAR image generation. The generated images can be directly used as training samples, thereby extending the training data set and improving the recognition accuracy.
- 18 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 16 (6) , 912-916
Synthetic Aperture Radar Image Generation With Deep Generative Models
A variety of machine learning approaches have been applied to synthetic aperture radar (SAR) automatic target recognition. The performances of these approaches rely strongly on the quality and quantity of training data. In real-world applications, however, it is challenging to obtain sufficient data suitable for these approaches. To alleviate this problem, a novel deep generative model for SAR image generation is proposed, which is an extension of Wasserstein autoencoder. The network structure and reconstruction loss function of the model have been improved according to the characteristics of SAR images. The experimental results demonstrate that our model is superior to other classical generative models in SAR image generation. The generated images can be directly used as training samples, thereby extending the training data set and improving the recognition accuracy.