Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging 事件

Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging arXiv:2606.02339v1 Announce Type: cross Abstract: Entropy minimization (EM) is the dominant objective for test-time adaptation, yet its failure mode, model collapse, remains poorly understood. In this work, we show that distribution shifts can cause feature clusters corresponding to distinct classes in the model's representation space to merge, while the decision boundary remains fixed. This induces a sys