Weijie Li

Weijie Li

Auto-generated profile, based on publicly available information

Weijie Li

College of Electronic Science and Technology, National University of Defense Technology, Changsha, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 January 2025 in IEEE Transactions on Image Processing
Verified
Journal Article
Open access
WLWeijie Li
Weijie Li
WYWei Yang
Wei Yang
Yuenan HouYuenan Hou
Yuenan Hou
LLLi Liu
Li Liu
YLYongxiang Liu
Yongxiang Liu
XLXiang Li
Xiang Li
Despite the remarkable progress in synthetic aperture radar automatic target recognition (SAR ATR), recent efforts have concentrated on detecting and classifying a specific category, e.g., vehicles, ships, airplanes, or buildings. One of the fundamental limitations of the top-performing SAR ATR methods is that the learning paradigm is supervised, task-specific, limited-category, closed-world learning, which depends on massive amounts of accurately annotated samples that are expensively labeled by expert SAR analysts and have limited generalization capability and scalability. In this work, we make the first attempt towards building a foundation model for SAR ATR, termed SARATR-X. SARATR-X learns generalizable representations via self-supervised learning (SSL) and provides a cornerstone for label-efficient model adaptation to generic SAR target detection and classification tasks. Specifically, SARATR-X is trained on 0.18 M unlabelled SAR target samples, which are curated by combining contemporary benchmarks and constitute the largest publicly available dataset till now. Considering the characteristics of SAR images, a backbone tailored for SAR ATR is carefully designed, and a two-step SSL method endowed with multi-scale gradient features was applied to ensure the feature diversity and model scalability of SARATR-X. The capabilities of SARATR-X are evaluated on classification under few-shot and robustness settings and detection across various categories and scenes, and impressive performance is achieved, often competitive with or even superior to prior fully supervised, semi-supervised, or self-supervised algorithms. Our SARATR-X and the curated dataset are released at https://github.com/waterdisappear/SARATR-X to foster research into foundation models for SAR image interpretation.

23 September 2024 in ISPRS Journal of Photogrammetry and Remote Sensing
Verified
Journal Article
Open access
WLWeijie Li
Weijie Li
WYWei Yang
Wei Yang
TLTianpeng Liu
Tianpeng Liu
Yuenan HouYuenan Hou
Yuenan Hou
YLYuxuan Li
Yuxuan Li
LLLi Liu
Li Liu

12 October 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
WLWeijie Li
Weijie Li
WYWei Yang
Wei Yang
WZWenpeng Zhang
Wenpeng Zhang
TLTianpeng Liu
Tianpeng Liu
YLYongxiang Liu
Yongxiang Liu
LLLi Liu
Li Liu
Vehicle recognition is a fundamental problem in SAR image interpretation. However, robustly recognizing vehicle targets is a challenging task in SAR due to the large intraclass variations and small interclass variations. Additionally, the lack of large datasets further complicates the task. Inspired by the analysis of target signature variations and deep learning explainability, this paper proposes a novel domain alignment framework named the Hierarchical Disentanglement-Alignment Network (HDANet) to achieve robustness under various operating conditions. Concisely, HDANet integrates feature disentanglement and alignment into a unified framework with three modules: domain data generation, multitask-assisted mask disentanglement, and domain alignment of target features. The first module generates diverse data for alignment, and three simple but effective data augmentation methods are designed to simulate target signature variations. The second module disentangles the target features from background clutter using the multitask-assisted mask to prevent clutter from interfering with subsequent alignment. The third module employs a contrastive loss for domain alignment to extract robust target features from generated diverse data and disentangled features. Lastly, the proposed method demonstrates impressive robustness across nine operating conditions in the MSTAR dataset, and extensive qualitative and quantitative analyses validate the effectiveness of our framework.

28 January 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
YLYongxiang Liu
Yongxiang Liu
WLWeijie Li
Weijie Li
LLLi Liu
Li Liu
JZJie Zhou
Jie Zhou
PBpeng bowen
peng bowen
XLXiang Li
Xiang Li
The absence of publicly available, large-scale, high-quality datasets for Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) has significantly hindered the application of rapidly advancing deep learning techniques, which hold huge potential to unlock new capabilities in this field. This is primarily because collecting large volumes of diverse target samples from SAR images is prohibitively expensive, largely due to privacy concerns, the characteristics of microwave radar imagery perception, and the need for specialized expertise in data annotation. Throughout the history of SAR ATR research, there have been only a number of small datasets, mainly including targets like ships, airplanes, buildings, etc. There is only one vehicle dataset MSTAR collected in the 1990s, which has been a valuable source for SAR ATR. To fill this gap, this paper introduces a large-scale, new dataset named ATRNet-STAR with 40 different vehicle categories collected under various realistic imaging conditions and scenes. It marks a substantial advancement in dataset scale and diversity, comprising over 190,000 well-annotated samples—$10\times$ larger than its predecessor, the famous MSTAR. Building such a large dataset is a challenging task, and the data collection scheme will be detailed. Second, we illustrate the value of ATRNet-STAR via extensively evaluating the performance of 15 representative methods with 7 different experimental settings on challenging classification and detection benchmarks derived from the dataset. Finally, based on our extensive experiments, we identify valuable insights for SAR ATR and discuss potential future research directions in this field. We hope that the scale, diversity, and benchmark of ATRNet-STAR can significantly facilitate the advancement of SAR ATR.

12 April 2023 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
WLWeijie Li
Weijie Li
WYWei Yang
Wei Yang
LLLi Liu
Li Liu
WZWenpeng Zhang
Wenpeng Zhang
YLYongxiang Liu
Yongxiang Liu
In recent years, deep learning has been widely used in SAR ATR and achieved excellent performance on the MSTAR dataset. However, due to constrained imaging conditions, MSTAR has data biases such as background correlation, i.e ., background clutter properties have a spurious correlation with target classes. Deep learning can overfit clutter to reduce training errors. Therefore, the degree of overfitting for clutter reflects the non-causality of deep learning in SAR ATR. Existing methods only qualitatively analyze this phenomenon. In this paper, we quantify the contributions of different regions to target recognition based on the Shapley value. The Shapley value of clutter measures the degree of overfitting. Moreover, we explain how data bias and model bias contribute to non-causality. Concisely, data bias leads to comparable signal-to-clutter ratios and clutter textures in training and test sets. And various model structures have different degrees of overfitting for these biases. The experimental results of various models under standard operating conditions on the MSTAR dataset support our conclusions. Our code is available at https://github.com/waterdisappear/Data-Bias-in-MSTAR.

30 June 2023 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
PKPeng Kou
Peng Kou
XQXiangfeng Qiu
Xiangfeng Qiu
YLYongxiang Liu
Yongxiang Liu
DZDongjie Zhao
Dongjie Zhao
WLWeijie Li
Weijie Li
SZShuanghui Zhang
Shuanghui Zhang
The inverse synthetic aperture radar (ISAR) images are often afflicted by boundary blurring, discontinuity, sidelobe effects of strong scattering points, a large dynamic range of gray values, and azimuth defocus, which pose significant challenges to image segmentation. This paper proposes a novel semantic segmentation method for ISAR images of space targets. The method is based on contrastive learning (CL) and Non-Local Unet (NL-Unet). First, the method roughly segments the target contour using binary semantic tags to remove sidelobe interference and image noise. Then, the Non-local self-attentive mechanism with a global perceptual field is used to exploit the structural symmetry of the ISAR image. Finally, to improve the segmentation ability of target small parts, the method adopts a training method based on CL to overcome the relatively weak problem of the supervised learning model. The proposed method outperforms existing methods on the simulated ISAR dataset. Moreover, it is practical and can be directly generalized to the real-measured dataset without retraining.