Extended Data Fig. 3: Experiment results showing short-cut learning successfully detected by CAML. | Nature Biomedical Engineering

Extended Data Fig. 3: Experiment results showing short-cut learning successfully detected by CAML.

From: Bridging the interpretability gap for medical artificial intelligence models using class-association manifold learning

Extended Data Fig. 3: Experiment results showing short-cut learning successfully detected by CAML.The alternative text for this image may have been generated using AI.

Cases revealing classifier shortcut learning behavior through CAML. a. Class-associated manifold from the PALM dataset. b. A series of images generated along the path, with classifier (trained on the PALM dataset where pathological myopia samples undergo brightness enhancement) predictions displayed above each image (values in parentheses indicate the predicted probability of pathological myopia). During counterfactual generation process, only brightness changes in the image, yet the classifier’s prediction shifts, indicating that the classifier uses brightness as a shortcut feature for pathological class identification.

Back to article page