Bias Mimicking: A Simple Sampling Approach for Bias Mitigation

Prior work has shown that Visual Recognition datasets frequently underrepresent bias groups $B$ (\eg Female) within class labels $Y$ (\eg Programmers). This dataset bias can lead to models that learn spurious correlations between class labels and bias groups such as age, gender, or race. Most recent methods that address this problem require significant architectural changes or additional loss functions requiring more hyper-parameter tuning. Alternatively, data sampling baselines from the class imbalance literature (\eg Undersampling, Upweighting), which can often be implemented in a single line of code and often have no hyperparameters, offer a cheaper and more efficient solution. However, these methods suffer from significant shortcomings. For example, Undersampling drops a significant part of the input distribution while Oversampling repeats samples, causing overfitting. To address these shortcomings, we introduce a new class conditioned sampling method: Bias Mimicking. The method is based on the observation that if a class $c$ bias distribution, \ie $P_D(B|Y=c)$ is mimicked across every $c^{\prime}\neq c$, then $P_D(Y|B) = P_D(B)$. Using this notion, BM, through a novel training procedure, ensures that the model is exposed to the entire distribution without repeating samples. Consequently, Bias Mimicking improves underrepresented groups average accuracy of sampling methods by 3\% over four benchmarks while maintaining and sometimes improving performance compared to non sampling methods.