AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP

Junsung Park, Jungbeom Lee, Jongyoon Song, Sangwon Yu, Dahuin Jung, Sungroh Yoon

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Unified any-modality language models · 22 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
use plausible objects (P1) instead of random objects (Rand-P1) (ablation)CLIP ViT-B/32 fine-tuning · VALSE (existence)accuracy: 73.78 -> 80.15Improved
use plausible objects (P1) instead of random objects (Rand-P1) (ablation)CLIP ViT-B/16 fine-tuning · VALSE (existence)accuracy: 76.22 -> 77.53Improved
use plausible objects (P1) instead of random objects (Rand-P1) (ablation)CLIP ViT-L/14@336px fine-tuning · VALSE (existence)accuracy: 76.22 -> 79.78Improved
add VQA-derived pipeline P2 to P1 (ablation)CLIP ViT-B/32 fine-tuning · VALSE (existence)accuracy: 80.15 -> 80.15No clear effect
add VQA-derived pipeline P2 to P1 (ablation)CLIP ViT-B/32 fine-tuning · NegRefCOCOgaccuracy: 63.18 -> 64.09Improved
add VQA-derived pipeline P2 to P1 (ablation)CLIP ViT-B/16 fine-tuning · VALSE (existence)accuracy: 77.53 -> 80.52Improved
add VQA-derived pipeline P2 to P1 (ablation)CLIP ViT-L/14 fine-tuning · NegRefCOCOgaccuracy: 60.23 -> 62.95Improved
fine-tune with generated captions instead of original captions (ablation)CLIP ViT-B/32 · VALSE (existence)accuracy: 68.35 -> 80.15Improved
fine-tune with original captions (ablation)CLIP ViT-B/32 · VALSE (existence)accuracy: 70.97 -> 68.35Hurt
fine-tune with generated captions instead of original captions (ablation)CLIP ViT-L/14@336px · VALSE (existence)accuracy: 73.97 -> 80.34Improved
swap SD-1.4 text encoder for NegationCLIP (no retraining)SD-1.4 · Text-to-image negation prompts (107 prompts)Neg Score: 0.295 -> 0.449Improved
swap SDXL-1.0 text encoders for NegationCLIPSDXL-1.0 · TIFATIFA: 0.849 -> 0.802Hurt

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