Learning Invariant Representation via Contrastive Feature Alignment for Clutter Robust SAR Target Recognition

by   Bowen Peng, et al.
National University of Defense Technology
NetEase, Inc

The deep neural networks (DNNs) have freed the synthetic aperture radar automatic target recognition (SAR ATR) from expertise-based feature designing and demonstrated superiority over conventional solutions. There has been shown the unique deficiency of ground vehicle benchmarks in shapes of strong background correlation results in DNNs overfitting the clutter and being non-robust to unfamiliar surroundings. However, the gap between fixed background model training and varying background application remains underexplored. Inspired by contrastive learning, this letter proposes a solution called Contrastive Feature Alignment (CFA) aiming to learn invariant representation for robust recognition. The proposed method contributes a mixed clutter variants generation strategy and a new inference branch equipped with channel-weighted mean square error (CWMSE) loss for invariant representation learning. In specific, the generation strategy is delicately designed to better attract clutter-sensitive deviation in feature space. The CWMSE loss is further devised to better contrast this deviation and align the deep features activated by the original images and corresponding clutter variants. The proposed CFA combines both classification and CWMSE losses to train the model jointly, which allows for the progressive learning of invariant target representation. Extensive evaluations on the MSTAR dataset and six DNN models prove the effectiveness of our proposal. The results demonstrated that the CFA-trained models are capable of recognizing targets among unfamiliar surroundings that are not included in the dataset, and are robust to varying signal-to-clutter ratios.


page 1

page 2

page 5


Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognition

Due to Synthetic Aperture Radar (SAR) imaging characteristics, SAR vehic...

Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense

Deep Neural Networks (DNNs) based Synthetic Aperture Radar (SAR) Automat...

Joint Embedding and Classification for SAR Target Recognition

Deep learning can be an effective and efficient means to automatically d...

Background Debiased SAR Target Recognition via Causal Interventional Regularizer

Recent studies have utilized deep learning (DL) techniques to automatica...

DGP-Net: Dense Graph Prototype Network for Few-Shot SAR Target Recognition

The inevitable feature deviation of synthetic aperture radar (SAR) image...

Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection

Shape deformation of targets in SAR image due to random orientation and ...

Please sign up or login with your details

Forgot password? Click here to reset