Adapted DINOv2 generalises better than task-specific medical segmentation nets
Only a small part of DINOv2 was adapted; in-distribution U-Nets stayed sharper and caught small lesions more often.
Stories per day · 30 days
1 RSS
Relatedbenchmark1biomedical-imaging1causal-inference1cell-painting1confounding1dinov21foundation-models1image-segmentation1jump-cp1medical-imaging1offline-reinforcement-learning1policy-optimization1
5 stories, newest first · one card per story
Stories tagged #domain-shift
Offline RL method handles domain shift and unmeasured confounding
CAT-CCB and CAT-CMDP use causal transportability and pessimistic optimization, with finite-sample suboptimality bounds.
BatchBench leaderboard tests AI robustness to biomedical batch effects
The leaderboard uses JUMP-CP Cell Painting images from unseen experimental batches and data sources.
Detecting a Shift Is Not Enough: Exact Minimax Limits of Linear Representation Repair
Exact minimax limits show linear shift repair needs far more calibration signal than detection.
AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition
AdaptVPR generates route-aware synthetic hard positives for visual place recognition, releasing the 160K-image AdaptCities dataset with R@1 gains up to 9.2% under domain shift.