Universal Debiased Editing for Fair Medical Image Classification

arXiv:2403.06104v1 Announce Type: new
Abstract: In the era of Foundation Models' (FMs) rising prominence in AI, our study addresses the challenge of biases in medical images while using FM API, particularly spurious correlations between pixels and sensitive attributes. Traditional methods for bias mitigation face limitations due to the restricted access to web-hosted FMs and difficulties in addressing the underlying bias encoded within the FM API. We propose an U(niversal) D(ebiased) E(diting) strategy, termed UDE, which generates UDE noise to mask …

abstract api arxiv bias biases challenge classification correlations cs.cv editing face fair foundation image images limitations medical pixels restricted access study type universal web