BatchBench: Benchmarking AI Robustness to Batch Effects and Domain Shift in Biomedical Images - A JUMP Cell Painting Leaderboard
arXiv cs.AI · 22 Oct 2026, 03:50 AEST
BatchBench is a new leaderboard designed to evaluate AI robustness in biomedical imaging. It focuses on performance under domain shifts and batch effects using the JUMP-CP dataset.
Key facts
- Despite recent advances, current AI systems remain highly susceptible to domain shifts, particularly in biomedical imaging, where images are usually acquired under substantially different experimental conditions.
- Although recent domain adaptation methods have made substantial progress, significant performance gaps under domain shift persist.
- BatchBench is built on JUMP-CP, one of the largest publicly available biomedical imaging datasets.
- Generated using the Cell Painting assay, JUMP-CP exhibits pronounced batch effects and domain shifts, making it a challenging testbed for evaluating robustness to distributional changes.
Read aloud
BatchBench is a new leaderboard designed to evaluate A I robustness in biomedical imaging. It focuses on performance under domain shifts and batch effects using the JUMP-CP dataset. Despite recent advances, current A I systems remain highly susceptible to domain shifts, particularly in biomedical imaging, where images are usually acquired under substantially different experimental conditions. Although recent domain adaptation methods have made substantial progress, significant performance gaps under domain shift persist. BatchBench is built on JUMP-CP, one of the largest publicly available biomedical imaging datasets. Generated using the Cell Painting assay, JUMP-CP exhibits pronounced batch effects and domain shifts, making it a challenging testbed for evaluating robustness to distributional changes.
Sources in this cluster
- BatchBench: Benchmarking AI Robustness to Batch Effects and Domain Shift in Biomedical Images - A JUMP Cell Painting Leaderboard
arXiv cs.AI · 22 Oct 2026, 03:50 AEST