Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation? 事件

Are We Overconfident in Models and Results for Semi-Supervised 3D Medical Image Segmentation? arXiv:2605.25561v1 Announce Type: new Abstract: Semi-supervised learning has become a dominant paradigm for reducing annotation costs. However, we argue that the current progress is clouded by a twofold overconfidence problem. Algorithmically, mainstream pseudo-labeling frameworks often conflate prediction confidence with uncertainty, leading to severe confirmation bias. Strategically, since multiple b