Technical report on target classification in SAR track

TL;DR

This paper introduces a robust SAR image classification method using a Swin Transformer backbone, enhanced with data augmentation, ReAct, and test time augmentation, achieving improved accuracy and uncertainty estimation.

Contribution

It presents a novel combination of transformer-based architecture with advanced techniques like ReAct and test time augmentation for SAR target classification.

Findings

Significant accuracy improvements with each technique

Enhanced out-of-distribution detection performance

Effective classification of maritime and atmospheric phenomena

Abstract

This report proposes a robust method for classifying oceanic and atmospheric phenomena using synthetic aperture radar (SAR) imagery. Our proposed method leverages the powerful pre-trained model Swin Transformer v2 Large as the backbone and employs carefully designed data augmentation and exponential moving average during training to enhance the model's generalization capability and stability. In the testing stage, a method called ReAct is utilized to rectify activation values and utilize Energy Score for more accurate measurement of model uncertainty, significantly improving out-of-distribution detection performance. Furthermore, test time augmentation is employed to enhance classification accuracy and prediction stability. Comprehensive experimental results demonstrate that each additional technique significantly improves classification accuracy, confirming their effectiveness in classifying maritime and atmospheric phenomena in SAR imagery.