Prototype Guided Pseudo Labeling and Perturbation-based Active Learning for domain adaptive semantic segmentation

Junkun Peng, Mingjie Sun, Eng Gee Lim, Qiufeng Wang, Jimin Xiao

Abstract: Highlights•A prototype-guided pseudo-label generation approach is suggested to maximize the utilization of varied source domain prototypes, thereby mitigating classifier prediction bias.•The perturbation-based uncertainty measurement is introduced to measure the prediction perturbation between the original target images and augmented ones.•A balanced schedule is designed to ensure that the perturbation plays a significant role in earlier selection rounds while later rounds are more driven by entropy uncertainty.