Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network

arXiv:2303.16564v3 Announce Type: replace
Abstract: The fairness of a deep neural network is strongly affected by dataset bias and spurious correlations, both of which are usually present in modern feature-rich and complex visual datasets. Due to the difficulty and variability of the task, no single de-biasing method has been universally successful. In particular, implicit methods not requiring explicit knowledge of bias variables are especially relevant for real-world applications. We propose a novel implicit mitigation method using a Bayesian neural network, …

abstract arxiv bayesian bias correlations cs.ai cs.cv dataset datasets deep neural network fairness feature modern network neural network posterior type visual