A Two-Stage Shake-Shake Network for Long-Tailed Recognition of SAR Aerial View Objects

Gongzhe Li, Linpeng Pan, Linwei Qiu, Zhiwen Tan, Fengying Xie, Haopeng Zhang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 249-256

Synthetic Aperture Radar (SAR) has received more attention due to its complementary superiority on capturing significant information in the remote sensing area. However, for an Aerial View Object Classification (AVOC) task, SAR images still suffer from the long-tailed distribution of the aerial view objects. This disparity dampens the performance of classification methods, especially for the data-sensitive deep learning models. In this paper, we propose a two-stage shake-shake network to tackle the long-tailed learning problem. Specifically, it decouples the learning procedure into the representation learning stage and the classification learning stage. Moreover, we apply the test time augmentation (TTA) and a post-processing approach (CAN) to improve the accuracy. In the PBVS 2022 Multi-modal Aerial View Object Classification Challenge Track 1, our method achieves 21.82% and 27.97% accuracy in the development phase and testing phase respectively, which achieves the top-tier among all the participants.