AI RESEARCH
Every Error has Its Magnitude: Asymmetric Mistake Severity Training for Multiclass Multiple Instance Learning
arXiv CS.CV
•
ArXi:2603.13682v1 Announce Type: new Multiple Instance Learning (MIL) has emerged as a promising paradigm for Whole Slide Image (WSI) diagnosis, offering effective learning with limited annotations. However, existing MIL frameworks overlook diagnostic priorities and fail to differentiate the severity of misclassifications in multiclass, leaving clinically critical errors unaddressed. We propose a mistake-severity-aware