Ask a Question

Prefer a chat interface with context about you and your work?

SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP

SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP

Large-scale vision-language models, such as CLIP, are known to contain harmful societal bias regarding protected attributes (e.g., gender and age). In this paper, we aim to address the problems of societal bias in CLIP. Although previous studies have proposed to debias societal bias through adversarial learning or test-time projecting, our …