← Search

Hyuntak Cha

2 accepted papers

2020

Learning from Failure: De-biasing Classifier from Biased Classifier

NeurIPS 2020poster

Neural networks often learn to make predictions that overly rely on spurious corre- lation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on the spuriously correlated attributes or presuming a particular bias type, we i…