Test-time bi-directional adaptation between image and model for robust segmentation

Xiaoqiong Huang, Xin Yang, Haoran Dou, Yuhao Huang, Li Zhang, Zhendong Liu, Zhongnuo Yan, Lian Liu, Yuxin Zou, Xindi Hu, Rui Gao, Yuanji Zhang, Yi Xiong, Wufeng Xue, Dong Ni

Abstract: Highlights•An effective test-time bi-directional adaptation strategy is proposed to seek robust segmentation.•A window-based order statistics alignment module is presented to adapt appearance-agnostic test images to existing learned models.•An augmented self-supervised learning is developed to adapt the segmentation model to images with unknown appearance shifts.•The method generalizes well across multi-vendor/center datasets.