Mining bias-target Alignment from Voronoi Cells

Rémi Nahon, Van-Tam Nguyen, Enzo Tartaglione; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023, pp. 4946-4955


Despite significant research efforts, deep neural networks remain vulnerable to biases: this raises concerns about their fairness and limits their generalization. In this paper, we propose a bias-agnostic approach to mitigate the impact of biases in deep neural networks. Unlike traditional debiasing approaches, we rely on a metric to quantify "bias alignment/misalignment" on target classes and use this information to discourage the propagation of bias-target alignment information through the network. We conduct experiments on several commonly used datasets for debiasing and compare our method with supervised and bias-specific approaches. Our results indicate that the proposed method achieves comparable performance to state-of-the-art supervised approaches, despite being bias-agnostic, even in the presence of multiple biases in the same sample.

Related Material

[pdf] [arXiv]
@InProceedings{Nahon_2023_ICCV, author = {Nahon, R\'emi and Nguyen, Van-Tam and Tartaglione, Enzo}, title = {Mining bias-target Alignment from Voronoi Cells}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {4946-4955} }