Consistency-Regularized GAN for Few-Shot SAR Target Recognition

TL;DR

This paper introduces Cr-GAN, a novel consistency-regularized GAN framework that synthesizes high-quality SAR images for few-shot recognition, overcoming data scarcity and improving accuracy significantly.

Contribution

Cr-GAN employs a dual-branch discriminator and novel interpolation and cycle consistency strategies to generate diverse, high-fidelity SAR samples with limited data, advancing few-shot SAR recognition.

Findings

Achieves 71.21% accuracy on MSTAR in 8-shot setting

Outperforms baseline models significantly

Requires only ~5% of diffusion model parameters

Abstract

Few-shot recognition in synthetic aperture radar (SAR) imagery remains a critical bottleneck for real-world applications due to extreme data scarcity. A promising strategy involves synthesizing a large dataset with a generative adversarial network (GAN), pre-training a model via self-supervised learning (SSL), and then fine-tuning on the few labeled samples. However, this approach faces a fundamental paradox: conventional GANs themselves require abundant data for stable training, contradicting the premise of few-shot learning. To resolve this, we propose the consistency-regularized generative adversarial network (Cr-GAN), a novel framework designed to synthesize diverse, high-fidelity samples even when trained under these severe data limitations. Cr-GAN introduces a dual-branch discriminator that decouples adversarial training from representation learning. This architecture enables a channel-wise feature interpolation strategy to create novel latent features, complemented by a dual-domain cycle consistency mechanism that ensures semantic integrity. Our Cr-GAN framework is adaptable to various GAN architectures, and its synthesized data effectively boosts multiple SSL algorithms. Extensive experiments on the MSTAR and SRSDD datasets validate our approach, with Cr-GAN achieving a highly competitive accuracy of 71.21% and 51.64%, respectively, in the 8-shot setting, significantly outperforming leading baselines, while requiring only ~5 of the parameters of state-of-the-art diffusion models. Code is available at: https://github.com/yikuizhai/Cr-GAN.