Saved in:
Bibliographic Details
Main Authors: Xiao, Junhao, Wu, Zhiyu, Lin, Hao, Chen, Yi, Liu, Yahui, Zhao, Xiaoran, Wang, Zixu, He, Zejiang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.21035
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Vision-Language Models (VLMs) like CLIP struggle to understand negation, often embedding affirmatives and negatives similarly (e.g., matching "no dog" with dog images). Existing methods refine negation understanding via fine-tuning CLIP's text encoder, risking overfitting. In this work, we propose CLIPGlasses, a plug-and-play framework that enhances CLIP's ability to comprehend negated visual descriptions. CLIPGlasses adopts a dual-stage design: a Lens module disentangles negated semantics from text embeddings, and a Frame module predicts context-aware repulsion strength, which is integrated into a modified similarity computation to penalize alignment with negated semantics, thereby reducing false positive matches. Experiments show that CLIP equipped with CLIPGlasses achieves competitive in-domain performance and outperforms state-of-the-art methods in cross-domain generalization. Its superiority is especially evident under low-resource conditions, indicating stronger robustness across domains.