CNNs trained on PadChest chest X-rays classify above chance even when the lungs are masked out, indicating shortcut learning, while glaucoma models on Chaksu rely more on expected anatomy.
Counterfactual contrastive learning: robust representations via causal image synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Mask of truth: model sensitivity to unexpected regions of medical images
CNNs trained on PadChest chest X-rays classify above chance even when the lungs are masked out, indicating shortcut learning, while glaucoma models on Chaksu rely more on expected anatomy.