Gamma Distribution PCA-Enhanced Feature Learning for Angle-Robust SAR Target Recognition

Chong Zhang, Peng Zhang, Mengke Li
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76778-76794, 2025.

Abstract

Scattering characteristics of synthetic aperture radar (SAR) targets are typically related to observed azimuth and depression angles. However, in practice, it is difficult to obtain adequate training samples at all observation angles, which probably leads to poor robustness of deep networks. In this paper, we first propose a Gamma-Distribution Principal Component Analysis ($\Gamma$PCA) model that fully accounts for the statistical characteristics of SAR data. The $\Gamma$PCA derives consistent convolution kernels to effectively capture the angle-invariant features of the same target at various attitude angles, thus alleviating deep models’ sensitivity to angle changes in SAR target recognition task. We validate $\Gamma$PCA model based on two commonly used backbones, ResNet and ViT, and conduct multiple robustness experiments on the MSTAR benchmark dataset. The experimental results demonstrate that $\Gamma$PCA effectively enables the model to withstand substantial distributional discrepancy caused by angle changes. Additionally, $\Gamma$PCA convolution kernel is designed to require no parameter updates, introducing no extra computational burden to the network. The source code is available at https://github.com/ChGrey/GammaPCA.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zhang25cy, title = {Gamma Distribution {PCA}-Enhanced Feature Learning for Angle-Robust {SAR} Target Recognition}, author = {Zhang, Chong and Zhang, Peng and Li, Mengke}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {76778--76794}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/zhang25cy/zhang25cy.pdf}, url = {https://proceedings.mlr.press/v267/zhang25cy.html}, abstract = {Scattering characteristics of synthetic aperture radar (SAR) targets are typically related to observed azimuth and depression angles. However, in practice, it is difficult to obtain adequate training samples at all observation angles, which probably leads to poor robustness of deep networks. In this paper, we first propose a Gamma-Distribution Principal Component Analysis ($\Gamma$PCA) model that fully accounts for the statistical characteristics of SAR data. The $\Gamma$PCA derives consistent convolution kernels to effectively capture the angle-invariant features of the same target at various attitude angles, thus alleviating deep models’ sensitivity to angle changes in SAR target recognition task. We validate $\Gamma$PCA model based on two commonly used backbones, ResNet and ViT, and conduct multiple robustness experiments on the MSTAR benchmark dataset. The experimental results demonstrate that $\Gamma$PCA effectively enables the model to withstand substantial distributional discrepancy caused by angle changes. Additionally, $\Gamma$PCA convolution kernel is designed to require no parameter updates, introducing no extra computational burden to the network. The source code is available at https://github.com/ChGrey/GammaPCA.} }
Endnote
%0 Conference Paper %T Gamma Distribution PCA-Enhanced Feature Learning for Angle-Robust SAR Target Recognition %A Chong Zhang %A Peng Zhang %A Mengke Li %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-zhang25cy %I PMLR %P 76778--76794 %U https://proceedings.mlr.press/v267/zhang25cy.html %V 267 %X Scattering characteristics of synthetic aperture radar (SAR) targets are typically related to observed azimuth and depression angles. However, in practice, it is difficult to obtain adequate training samples at all observation angles, which probably leads to poor robustness of deep networks. In this paper, we first propose a Gamma-Distribution Principal Component Analysis ($\Gamma$PCA) model that fully accounts for the statistical characteristics of SAR data. The $\Gamma$PCA derives consistent convolution kernels to effectively capture the angle-invariant features of the same target at various attitude angles, thus alleviating deep models’ sensitivity to angle changes in SAR target recognition task. We validate $\Gamma$PCA model based on two commonly used backbones, ResNet and ViT, and conduct multiple robustness experiments on the MSTAR benchmark dataset. The experimental results demonstrate that $\Gamma$PCA effectively enables the model to withstand substantial distributional discrepancy caused by angle changes. Additionally, $\Gamma$PCA convolution kernel is designed to require no parameter updates, introducing no extra computational burden to the network. The source code is available at https://github.com/ChGrey/GammaPCA.
APA
Zhang, C., Zhang, P. & Li, M.. (2025). Gamma Distribution PCA-Enhanced Feature Learning for Angle-Robust SAR Target Recognition. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:76778-76794 Available from https://proceedings.mlr.press/v267/zhang25cy.html.

Related Material