Loading [a11y]/accessibility-menu.js
Class Hierarchy Aware Contrastive Feature Learning for Multigranularity SAR Target Recognition | IEEE Journals & Magazine | IEEE Xplore

Class Hierarchy Aware Contrastive Feature Learning for Multigranularity SAR Target Recognition


Abstract:

Deep learning has emerged as the dominant paradigm for synthetic aperture radar (SAR) automatic target recognition (ATR). However, existing learning algorithms focus prim...Show More

Abstract:

Deep learning has emerged as the dominant paradigm for synthetic aperture radar (SAR) automatic target recognition (ATR). However, existing learning algorithms focus primarily on single-granularity categorical recognition tasks without fully exploiting the high-order correlations among both data and label domains. This article presents a multigranularity SAR ATR framework called class hierarchy aware contrastive feature learning. The framework consists of three modules designed to extract higher-order discriminative features, enforce hierarchical feature distribution, and enable hierarchically consistent classification. The feature extractor module extracts higher-order class-specific features from two groups of multiview samples, breaking the assumption of i.i.d. data. Furthermore, we introduce a structured contrastive regularization module to enforce a hierarchical distribution in the feature domain, thereby improving the discriminative power of the learned representations and addressing the issue of hierarchical violation. In addition, an effective multigranularity label representation scheme and a hierarchical classifier are developed to leverage the hierarchical relationships among classes. The framework contributes to advancing SAR ATR by providing insights into hierarchical category-aware feature learning and classification and improving the generalization ability in scenarios with limited training samples. Experimental evaluations conducted on a benchmark SAR dataset validate the effectiveness of the proposed framework. Particularly, in scenarios with limited training samples and zero-shot ATR, our framework outperforms state-of-the-art methods, achieving better performance.
Published in: IEEE Transactions on Aerospace and Electronic Systems ( Volume: 60, Issue: 6, December 2024)
Page(s): 7962 - 7977
Date of Publication: 02 July 2024

ISSN Information:

Funding Agency:


References

References is not available for this document.