Benchmark shows that combining data rebalancing with feature disentanglement mitigates shortcut learning more effectively than rebalancing alone in medical imaging models.
Learning debiased representation via disentangled feature augmentation.Advances in Neural Information Processing Systems, 34:25123–25133, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study
Benchmark shows that combining data rebalancing with feature disentanglement mitigates shortcut learning more effectively than rebalancing alone in medical imaging models.