2025
Co-training with Progressive Distribution Alignment and Uncertainty-Interactive Relabeling for Semi-Supervised Domain Adaptive Semantic Segmentation
ICASSP 2025accepted
Self-training is a strong baseline for semi-supervised domain adaptive semantic segmentation. However, it inevitably introduces biased links between features and concepts in the prediction of certain "hard pixels", which may mislead the generalization of models. We consider these hard pixels to come…