Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR

TL;DR

This paper introduces a weakly contrastive learning framework for SAR ATR that achieves high accuracy with limited labeled data by moderating embedding distances and clustering features.

Contribution

The novel BIDFC framework combines weakly contrastive learning with a dynamic clustering loss, enabling effective SAR ATR with minimal labeled data.

Findings

Achieved 91.25% accuracy on MSTAR with only 3.13% training data.

High linear evaluation accuracy of 90.13% on the same dataset.

Demonstrated generalization to the OpenSarShip dataset.

Abstract

In recent years, impressive performance of deep learning technology has been recognized in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). Since a large amount of annotated data is required in this technique, it poses a trenchant challenge to the issue of obtaining a high recognition rate through less labeled data. To overcome this problem, inspired by the contrastive learning, we proposed a novel framework named Batch Instance Discrimination and Feature Clustering (BIDFC). In this framework, different from that of the objective of general contrastive learning methods, embedding distance between samples should be moderate because of the high similarity between samples in the SAR images. Consequently, our flexible framework is equipped with adjustable distance between embedding, which we term as weakly contrastive learning. Technically, instance labels are assigned to the unlabeled data in per batch and random augmentation and training are performed few times on these augmented data. Meanwhile, a novel Dynamic-Weighted Variance loss (DWV loss) function is also posed to cluster the embedding of enhanced versions for each sample. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) database indicate a 91.25% classification accuracy of our method fine-tuned on only 3.13% training data. Even though a linear evaluation is performed on the same training data, the accuracy can still reach 90.13%. We also verified the effectiveness of BIDFC in OpenSarShip database, indicating that our method can be generalized to other datasets. Our code is avaliable at: https://github.com/Wenlve-Zhou/BIDFC-master.