Learning from Failure: De-biasing Classifier from Biased Classifier

By J. Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee, Jinwoo Shin. Neural Information Processing Systems, 2020

416 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations (2022, methodology): “Several methods have been proposed for the scenario where group labels are not known, and need to be inferred from the data; these methods typically train a pair of networks, where the first model is used to identify the challenging minority examples and define a weighted loss for the second model [”