AI Paper Atlas

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

Not Just What’s There: Enabling CLIP to Comprehend Negated Visual Descriptions Without Fine-Tuning

Junhao Xiao, Zhiyu Wu, Hao Lin, Yi Chen, Yahui Liu, Xiaoran Zhao, Zixu Wang, Zejiang He

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Fine-grained improvements to CLIP · 5 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 syntax stream in Lens (ablation)CLIPGlasses · CC-Negaccuracy: 94.09% -> 96.56%Improved
add syntax stream in Lens (ablation)CLIPGlasses · CC-NegFAR: 4.4927 -> 7.8253Improved
add semantic stream in Lens (ablation)CLIPGlasses · CC-Negaccuracy: 94.93% -> 96.56%Improved
add residual gating in Lens (ablation)CLIPGlasses · CC-Negaccuracy: 68.93% -> 96.56%Improved
add cross-modal context in Frame (ablation)CLIPGlasses · CC-Negaccuracy: 93.79% -> 96.56%Improved
add dynamic repulsion weight (Frame) (ablation)CLIPGlasses · CC-Negaccuracy: 63.74% -> 96.56%Improved
add cross-modal context in Frame (ablation)CLIPGlasses · CC-NegFAR: 7.3051 -> 7.8253Improved
CLIPGlasses vs CoN-CLIP trained on CC-NegCoN-CLIP · Neg-COCO-MCQaccuracy: 25.70% -> 34.51%Improved
CLIPGlasses vs CoN-CLIP trained on Neg-COCO-RCoN-CLIP · CC-Neg-valaccuracy: 65.91% -> 93.36%Improved
CLIPGlasses vs CoN-CLIP trained on Neg-COCO-RCoN-CLIP · Neg-COCO-MCQaccuracy: 30.61% -> 35.90%Improved
CLIPGlasses vs CoN-CLIP in-domainCoN-CLIP · CC-Neg-valaccuracy: 99.70% -> 96.56%Hurt
fine-tune CLIP text encoder on negation data (CoN-CLIP) vs vanillaVanilla CLIP · ImageNet zero-shotaccuracy: 53.87 -> 50.98Hurt

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