BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers

ArXi:2605.28450v1 Announce Type: cross Visual data from the Web power image classifiers, which often underpin many web services, such as recommendation and content moderation. However, the raw Web data often contain spurious correlations and social biases, and neural networks are known for their tendency to learn biases present in data. This can reinforce unfairness in web services and the web data, leading to a vicious cycle.