Review for NeurIPS paper: Learning from Failure: De-biasing Classifier from Biased Classifier

Weaknesses: 1. LfF does use human knowledge; please do not claim that it doesn't. The paper criticises prior works on the de-biasing problem for using "domain-specific knowledge" or "explicit supervision" on the suprious correlated attributes, while claiming their methods to be designed for scenarios where "such information is unavailable". I strongly disagree with this bold claim. LfF heavily depends on the assumption that the quickly-learned cues (so-called "malignant biases") are the undesired biases that hinders generalisation. Do quickly-learned cues **always** correspond to undesired set of biases?