Looking at Model Debiasing through the Lens of Anomaly Detection

TL;DR

This paper introduces a novel bias identification method based on anomaly detection, which effectively detects bias-conflicting samples in neural networks, leading to improved bias mitigation without complex debiasing techniques.

Contribution

The work proposes a new out-of-distribution perspective for bias detection using anomaly detection, enabling effective bias mitigation through data upsampling and augmentation.

Findings

Achieves state-of-the-art results on synthetic and real datasets.

Shows that accurate bias identification can reduce the need for complex debiasing methods.

Demonstrates the effectiveness of anomaly detection in bias mitigation.

Abstract

It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization abilities and low performance. In this context, model debiasing approaches can be devised aiming at reducing the model's dependency on such unwanted correlations, either leveraging the knowledge of bias information or not. In this work, we focus on the latter and more realistic scenario, showing the importance of accurately predicting the bias-conflicting and bias-aligned samples to obtain compelling performance in bias mitigation. On this ground, we propose to conceive the problem of model bias from an out-of-distribution perspective, introducing a new bias identification method based on anomaly detection. We claim that when data is mostly biased, bias-conflicting samples can be regarded as outliers with respect to the bias-aligned distribution in the feature space of a biased model, thus allowing for precisely detecting them with an anomaly detection method. Coupling the proposed bias identification approach with bias-conflicting data upsampling and augmentation in a two-step strategy, we reach state-of-the-art performance on synthetic and real benchmark datasets. Ultimately, our proposed approach shows that the data bias issue does not necessarily require complex debiasing methods, given that an accurate bias identification procedure is defined. Source code is available at https://github.com/Malga-Vision/MoDAD