Balanced Prompt Adaptation against Entropy-Induced Collapse for Test-Time Binary Segmentation
Entropy minimization is a standard objective for test-time adaptation (TTA), but it can fail in imbalanced binary segmentation. Unlike image classification, dense segmentation aggregates thousands of pixel predictions, allowing the larger predicted class to dominate the update, pull minority predictions toward itself, and produce a degenerate mask as predictions saturate and their entropy…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
