نسخة أولية وصول مفتوح
MOXIE: Discovering Alternative Explanations for Biomedical Image Classifiers
Segment-based explanation methods such as LIME return a single explanation for each prediction, computed from one fixed image segmentation. This hides two important facts: a prediction can be supported by many different sets of image segments, and the segmentation itself shapes which explanations can be found. We intro …