Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models

arXiv:2311.16254v2 Announce Type: replace
Abstract: Large-scale vision-and-language models, such as CLIP, are typically trained on web-scale data, which can introduce inappropriate content and lead to the development of unsafe and biased behavior. This, in turn, hampers their applicability in sensitive and trustworthy contexts and could raise significant concerns in their adoption. Our research introduces a novel approach to enhancing the safety of vision-and-language models by diminishing their sensitivity to NSFW (not safe for work) inputs. In particular, our methodology seeks …

arxiv clip concepts cs.ai cs.cl cs.cv cs.mm language language models nsfw safe type vision vision-and-language