Unimore logo AImageLab

ClusterFix: A Cluster-Based Debiasing Approach without Protected-Group Supervision

Abstract: The failures of Deep Networks can sometimes be ascribed to biases in the data or algorithmic choices. Existing debiasing approaches exploit prior knowledge to avoid unintended solutions; we acknowledge that, in real-world settings, it could be unfeasible to gather enough prior information to characterize the bias, or it could even raise ethical considerations. We hence propose a novel debiasing approach, termed ClusterFix, which does not require any external hint about the nature of biases. Such an approach alters the standard empirical risk minimization and introduces a per-example weight, encoding how critical and far from the majority an example is. Notably, the weights consider how difficult it is for the model to infer the correct pseudo-label, which is obtained in a self-supervised manner by dividing examples into multiple clusters. Extensive experiments show that the misclassification error incurred in identifying the correct cluster allows for identifying examples prone to bias-related issues. As a result, our approach outperforms existing methods on standard benchmarks for bias removal and fairness.


Citation:

Capitani, Giacomo; Bolelli, Federico; Porrello, Angelo; Calderara, Simone; Ficarra, Elisa "ClusterFix: A Cluster-Based Debiasing Approach without Protected-Group Supervision" 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, Hawaii, pp. 4858 -4867 , Jan 4-8, 2024 DOI: 10.1109/WACV57701.2024.00480

 not available

Paper download: