Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation

TL;DR

This paper introduces a novel approach using self-supervision and self-distillation to effectively mitigate biases in visual recognition models trained on limited data, outperforming existing methods.

Contribution

It demonstrates for the first time that self-supervision and self-distillation can be used for bias mitigation in limited data scenarios, improving fairness and accuracy.

Findings

Significantly reduces bias scores on skewed datasets

Enhances performance of existing bias mitigation methods

Outperforms baseline models in accuracy and fairness

Abstract

Deep learning models generally learn the biases present in the training data. Researchers have proposed several approaches to mitigate such biases and make the model fair. Bias mitigation techniques assume that a sufficiently large number of training examples are present. However, we observe that if the training data is limited, then the effectiveness of bias mitigation methods is severely degraded. In this paper, we propose a novel approach to address this problem. Specifically, we adapt self-supervision and self-distillation to reduce the impact of biases on the model in this setting. Self-supervision and self-distillation are not used for bias mitigation. However, through this work, we demonstrate for the first time that these techniques are very effective in bias mitigation. We empirically show that our approach can significantly reduce the biases learned by the model. Further, we experimentally demonstrate that our approach is complementary to other bias mitigation strategies. Our approach significantly improves their performance and further reduces the model biases in the limited data regime. Specifically, on the L-CIFAR-10S skewed dataset, our approach significantly reduces the bias score of the baseline model by 78.22% and outperforms it in terms of accuracy by a significant absolute margin of 8.89%. It also significantly reduces the bias score for the state-of-the-art domain independent bias mitigation method by 59.26% and improves its performance by a significant absolute margin of 7.08%.