Saved in:
Bibliographic Details
Main Authors: Wei, WenZhang, Gui, Zhipeng, Peng, Dehua, Ye, Tiandi, Wu, Huayi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.30968
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913172297875456
author Wei, WenZhang
Gui, Zhipeng
Peng, Dehua
Ye, Tiandi
Wu, Huayi
author_facet Wei, WenZhang
Gui, Zhipeng
Peng, Dehua
Ye, Tiandi
Wu, Huayi
contents The core of vision-language models lies in measuring cross-modal similarity within a unified representation space. However, most image-text matching or multi-class image classification datasets lack fine-grained cross-modal matching annotations, forcing the continuous similarity space into binary classification boundaries. This compression induces false negative samples and significantly impairs the generalization performance of cross-modal tasks. While prior research has attempted to mitigate this by modeling intra-modal ambiguity, it often overlooks inherent annotation flaws, leading to suboptimal uncertainty allocation. To address these challenges, we propose a Variational Adapter for Cross-modal Similarity Representation (VACSR). This approach reformulates image-text matching with fine-grained semantic scarcity as a variational inference problem. It constructs a latent space for cross-modal similarity and uses regularization techniques to mitigate overfitting to binary annotations. Experiments on image-text retrieval, domain generalization, and base-to-novel generalization demonstrate the proposed method's effectiveness and robust generalization ability.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30968
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Variational Adapter for Cross-modal Similarity Representation
Wei, WenZhang
Gui, Zhipeng
Peng, Dehua
Ye, Tiandi
Wu, Huayi
Computer Vision and Pattern Recognition
Artificial Intelligence
The core of vision-language models lies in measuring cross-modal similarity within a unified representation space. However, most image-text matching or multi-class image classification datasets lack fine-grained cross-modal matching annotations, forcing the continuous similarity space into binary classification boundaries. This compression induces false negative samples and significantly impairs the generalization performance of cross-modal tasks. While prior research has attempted to mitigate this by modeling intra-modal ambiguity, it often overlooks inherent annotation flaws, leading to suboptimal uncertainty allocation. To address these challenges, we propose a Variational Adapter for Cross-modal Similarity Representation (VACSR). This approach reformulates image-text matching with fine-grained semantic scarcity as a variational inference problem. It constructs a latent space for cross-modal similarity and uses regularization techniques to mitigate overfitting to binary annotations. Experiments on image-text retrieval, domain generalization, and base-to-novel generalization demonstrate the proposed method's effectiveness and robust generalization ability.
title Variational Adapter for Cross-modal Similarity Representation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.30968