31 citations · 49 across the 9 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021
Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment
Bowen Zhao, Chen Chen, Qian-Wei Wang +2
Models notoriously suffer from dataset biases which are detrimental to robustness and generalization. The identify-emphasize paradigm shows a promising effect in dealing with unkno…
cs.LG2021★ 1 cited
Energy Aligning for Biased Models
Bowen Zhao, Chen Chen, Qi Ju +1
Training on class-imbalanced data usually results in biased models that tend to predict samples into the majority classes, which is a common and notorious problem. From the perspec…