Semi-Supervised SAR ATR via Epoch- and Uncertainty-Aware Pseudo-Label Exploitation
Xinzheng Zhang, Yuqing Luo, Liping Hu
Abstract
Automatic target recognition (ATR) is a significant application scenario for Synthetic aperture radar (SAR) image interpretation. In recent years, deep-learning based SAR ATR approaches have made great progress, with the require of large amounts of labeled data for network training. However, the labeled SAR images are scarce, and the annotation of SAR images is expensive and time-consuming. In this paper, a novel semi-supervised learning (SSL) framework is proposed for SAR ATR, which effectively alleviates the need of labeled samples for network training, and allows for excavating the intrinsic semantic relationship information between samples belonging to different categories, greatly improving recognition performance. This method develops an epoch- and uncertainty-aware pseudo-label selection (EUAPS) mechanism, which takes advantage of the underutilized consistency between training epochs, and introduces the uncertainty estimates. EUAPS can select pseudo-label samples with high-confidence, allowing the network to perform well even when labels are extremely scarce. Furthermore, we propose a novel loss function, group relationship consistency loss (GRCL) that explicitly enforces the consistency of relations between different samples under perturbations. GRCL facilitates the network to learn rich sample relationship information and more discriminative features in sample group level, effectively reducing the recognition error rate. Extensive experiments were carried out on three public benchmark SAR datasets. And the experimental results illustrate that the proposed approach achieves the accuracy of 98.58% when 10 labeled samples per class and 88.65% when only 5 labeled samples per class respectively, outperforming the state-of-the-art SSL methods and demonstrating the superiority.