AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

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

Samuele Poppi, Tobia Poppi, Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Fine-grained improvements to CLIP · 36 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add inappropriate content redirection losses to the fine-tuning (ablation)Safe-CLIP · ViSU test set, T*-to-V∪V*R@10: 30.4 -> 46.9Improved
add negative cosine similarity (single-modality redirect) losses (ablation)Safe-CLIP · ViSU test set, safe T-to-VR@1: 41.9 -> 45.9Improved
add negative cosine similarity losses (ablation)Safe-CLIP · ViSU test set, V*-to-T∪T*R@1: 13.7 -> 19.1Improved
add inappropriate content redirection losses (ablation)Safe-CLIP · ViSU test set, safe T-to-VR@1: 49.9 -> 45.9Hurt
replace CLIP text encoder with Safe-CLIP in Stable Diffusion v1.4Stable Diffusion v1.4 · ViSU promptsprobability of unsafe image (%): 26.2 -> 3.6Improved
add Safe-CLIP on top of SLD-StrongSLD-Strong · I2P prompts (avg)probability of unsafe image (%): 13.5 -> 13.0Improved
use Safe-CLIP visual encoder in LLaVALLaVA · NudeNet NSFW images% NSFW text: 62.6 -> 26.7Improved
add SFT of Llama 2-Chat on safe-unsafe pairs (ablation)NSFW text generator · ViSU text, GPT-3.5 NSFW% NSFW: 9.3 -> 75.0Improved
add DPO stage after SFT (ablation)NSFW text generator · ViSU text, GPT-3.5 NSFW% NSFW: 75.0 -> 79.1Improved
fine-tune with Safe-CLIP versus DataComp-1B cleaned-data CLIPCLIP · Real NSFW images, text-to-image (NudeNet)% NSFW retrieved: 55.6 -> 8.4Improved

Later papers that compared with this method

2 later accepted papers report Safe-CLIP as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy