APPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigation

arXiv:2403.05114v1 Announce Type: new
Abstract: Ensuring fairness in deep-learning-based segmentors is crucial for health equity. Much effort has been dedicated to mitigating unfairness in the training datasets or procedures. However, with the increasing prevalence of foundation models in medical image analysis, it is hard to train fair models from scratch while preserving utility. In this paper, we propose a novel method, Adversarial Privacy-aware Perturbations on Latent Embedding (APPLE), that can improve the fairness of deployed segmentors by introducing a small …

abstract adversarial analysis apple arxiv cs.cv datasets embedding equity fair fairness foundation health health equity however image medical privacy scratch train training training datasets type