Physics-Grounded Adversarial Stain Augmentation with Calibrated Coverage Guarantees

arXiv:2605.13889v1 Announce Type: cross Abstract: Stain variation across hospitals degrades histopathology models at deployment. Existing augmentation methods perturb color spaces with arbitrary hyperparameters, lacking both a principled budget and coverage guarantees for unseen centers. We propose extbf{C}alibrated extbf{A}dversarial extbf{S}tain extbf{A}ugmentation (extbf{CASA}), which performs adversarial augmentation in the Macenko stain parameter space with a budget calibrated from multi-center statistics via the DKW inequality. On Camelyon17-WILDS (5 seeds), CASA achieves 93.9% pm 1.6% slide-level accuracy -- outperforming HED-strong (88.4% pm 7.3%), RandStainNA (85.2% pm 6.7%), and ERM (63.9% pm 11.3%) -- with the highest worst-group accuracy (84.9% pm 0.9%) among all 10 compared methods.

Source: arXiv cs.CV | 2026-05-15