Journal article · 2026 · Open access
Filtering Critical Regions and Enhancing Discriminative Features With Transformer for Aircraft Recognition in SAR Images
IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15 · Published 13 November 2026 · DOI 10.1109/tnnls.2026.3748628
In brief
“Filtering Critical Regions and Enhancing Discriminative Features With Transformer for Aircraft Recognition in SAR Images” is a 2026 journal article by Yuanzhe Shang and 7 co-authors, published in IEEE Transactions on Neural Networks and Learning Systems. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Neural Networks and Learning Systems.
- Citations
- 0
- Authors
- 8
Abstract
Aircraft automatic target recognition (ATR) in synthetic aperture radar (SAR) images has significant application value. But the component scattering discreteness and complex background interference have posed significant challenges in SAR aircraft ATR. Due to these challenges, directly performing feature extraction based on the entire image may focus on useless even harmful regions. To achieve discriminative feature representation, a more practical SAR aircraft ATR scheme is proposed to filter critical regions and enhance discriminative features (FCED) with transformer, which is composed of three key components: global assisted branch (GAB), local enhanced branch (LEB) and multigranularity discriminative loss (MGDL). First, the GAB is designed to decouple background interference from aircraft targets by generating a critical region filter (CRF), which utilizes weighted voting strategy and the innate advantages of transformer structure. Then, leveraging the decision mask determined by CRF, the LEB is composed of a key part selector followed by successive graph convolutional network (GCN) to model the structural relationships between the key parts of aircraft, thereby enhancing discriminative features. Finally, the MGDL jointly updates the GAB, LEB, and the CRF, and forces the model to extract features with increased innerclass compactness and interclass separability. Experimental results on the benchmark dataset FAIR-CSAR verify the effectiveness of our design. This work represents the first attempt to filter critical aircraft regions in SAR images by leveraging the innate capabilities of the vision transformer (ViT) structure. We hope our exploration can provide a new perspective in SAR ATR community.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Shang, Y., Pu, W., Xu, R., Huang, Y., Zhang, Y., Wu, J., Yang, J., & Wu, J. (2026). Filtering Critical Regions and Enhancing Discriminative Features With Transformer for Aircraft Recognition in SAR Images. IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15. https://doi.org/10.1109/tnnls.2026.3748628
MLA 9
Shang, Yuanzhe, et al. “Filtering Critical Regions and Enhancing Discriminative Features With Transformer for Aircraft Recognition in SAR Images.” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, 2026, pp. 1–15. https://doi.org/10.1109/tnnls.2026.3748628.
Chicago
Shang, Yuanzhe, Wei Pu, Renjie Xu, Yulin Huang, Yin Zhang, Junjie Wu, Jie Yang, and Jianqi Wu. 2026. “Filtering Critical Regions and Enhancing Discriminative Features With Transformer for Aircraft Recognition in SAR Images.” IEEE Transactions on Neural Networks and Learning Systems PP: 1–15. https://doi.org/10.1109/tnnls.2026.3748628.
Harvard
Shang, Y. et al. (2026) ‘Filtering Critical Regions and Enhancing Discriminative Features With Transformer for Aircraft Recognition in SAR Images’, IEEE Transactions on Neural Networks and Learning Systems, PP, pp. 1–15. doi:10.1109/tnnls.2026.3748628.
IEEE
Y. Shang et al., “Filtering Critical Regions and Enhancing Discriminative Features With Transformer for Aircraft Recognition in SAR Images,” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, pp. 1–15, 2026, doi: 10.1109/tnnls.2026.3748628.
BibTeX
@article{shang2026filtering,
title = {{Filtering Critical Regions and Enhancing Discriminative Features With Transformer for Aircraft Recognition in SAR Images}},
author = {Shang, Yuanzhe and Pu, Wei and Xu, Renjie and Huang, Yulin and Zhang, Yin and Wu, Junjie and Yang, Jie and Wu, Jianqi},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
year = {2026},
volume = {PP},
pages = {1--15},
doi = {10.1109/tnnls.2026.3748628},
url = {https://doi.org/10.1109/tnnls.2026.3748628}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Engineering › Aerospace Engineering › Advanced SAR Imaging Techniques
- synthetic aperture radar images
- vision transformer
- graph convolutional networks
- weighted voting
- background interference
Work with this paper
Most-cited papers in Engineering
- A Closed‐form Equation for Predicting the Hydraulic Conductivity of Unsaturated SoilsMartinus Th. van Genuchten · Soil Science Society of America Journal · 1980 · 28,197 citations
- An improved technique for determining hardness and elastic modulus using load and displacement sensing indentation experimentsW. C. Oliver, George M. Pharr · Journal of materials research/Pratt's guide to venture capital sources · 1992 · 27,379 citations
- Digital communicationsOwen Bishop · Routledge eBooks · 2007 · 24,890 citations
- The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysisNorden Eh Huang, Zhengwei Shen, Steven R. Long and 6 more · Proceedings of the Royal Society A Mathematical Physical and Engineering Sciences · 1998 · 24,008 citations
- Numerical Heat Transfer and Fluid FlowSuhas V. Patankar · CRC Press eBooks · 2018 · 23,491 citations
Questions about this paper
How do I cite this paper in APA style?
Shang, Y., Pu, W., Xu, R., Huang, Y., Zhang, Y., Wu, J., Yang, J., & Wu, J. (2026). Filtering Critical Regions and Enhancing Discriminative Features With Transformer for Aircraft Recognition in SAR Images. IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15. https://doi.org/10.1109/tnnls.2026.3748628
How many times has this paper been cited?
0 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at IEEE Transactions on Neural Networks and Learning Systems: sign in and open the full text from this page.
Who wrote this paper?
Yuanzhe Shang, Wei Pu, Renjie Xu, Yulin Huang, Yin Zhang, Junjie Wu, Jie Yang, Jianqi Wu.
What is the DOI of this paper?
10.1109/tnnls.2026.3748628, permanently at https://doi.org/10.1109/tnnls.2026.3748628. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.