HarmoCLIP: Harmonizing Global and Regional Representations in Contrastive Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zeng, Haoxi, Li, Haoxuan, Bin, Yi, Zeng, Pengpeng, Xu, Xing, Yang, Yang, Shen, Heng Tao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909930846420992
author Zeng, Haoxi
Li, Haoxuan
Bin, Yi
Zeng, Pengpeng
Xu, Xing
Yang, Yang
Shen, Heng Tao
author_facet Zeng, Haoxi
Li, Haoxuan
Bin, Yi
Zeng, Pengpeng
Xu, Xing
Yang, Yang
Shen, Heng Tao
contents Contrastive Language-Image Pre-training (CLIP) has demonstrated remarkable generalization ability and strong performance across a wide range of vision-language tasks. However, due to the lack of region-level supervision, CLIP exhibits limited fine-grained semantic understanding. Although several methods attempt to mitigate this issue, they unintentionally disrupt the global alignment, resulting in a persistent trade-off where improving local perception simultaneously degrades global coherence. In this paper, we propose HarmoCLIP, a novel framework designed to harmonize global and region representations within CLIP. We first identify that the absence of direct alignment between local textual and visual semantics is the fundamental cause of the trade-off. To address this, HarmoCLIP introduces an explicit fine-grained semantic supervision term that directly aligns textual segments with their corresponding visual regions, effectively bridging the image region space and the textual space. To further strengthen the representation capability at the local level, our method introduces a novel Region-Language Alignment supervision strategy that promotes fine-grained semantic learning without compromising global semantic consistency. Extensive experiments demonstrate that HarmoCLIP achieves state-of-the-art (improvement up to 69.78%) performance on the global task of retrieval and yields a substantial 3.2% improvement in Top-1 accuracy on the region task of bounding-box classification, consistently outperforming prior approaches while providing a balanced, efficient, and plug-and-play solution to the global-local trade-off in CLIP. Code is available at https://github.com/Erosist/HarmoCLIP.
format Preprint
id arxiv_https___arxiv_org_abs_2511_22594
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HarmoCLIP: Harmonizing Global and Regional Representations in Contrastive Vision-Language Models
Zeng, Haoxi
Li, Haoxuan
Bin, Yi
Zeng, Pengpeng
Xu, Xing
Yang, Yang
Shen, Heng Tao
Computer Vision and Pattern Recognition
Artificial Intelligence
Contrastive Language-Image Pre-training (CLIP) has demonstrated remarkable generalization ability and strong performance across a wide range of vision-language tasks. However, due to the lack of region-level supervision, CLIP exhibits limited fine-grained semantic understanding. Although several methods attempt to mitigate this issue, they unintentionally disrupt the global alignment, resulting in a persistent trade-off where improving local perception simultaneously degrades global coherence. In this paper, we propose HarmoCLIP, a novel framework designed to harmonize global and region representations within CLIP. We first identify that the absence of direct alignment between local textual and visual semantics is the fundamental cause of the trade-off. To address this, HarmoCLIP introduces an explicit fine-grained semantic supervision term that directly aligns textual segments with their corresponding visual regions, effectively bridging the image region space and the textual space. To further strengthen the representation capability at the local level, our method introduces a novel Region-Language Alignment supervision strategy that promotes fine-grained semantic learning without compromising global semantic consistency. Extensive experiments demonstrate that HarmoCLIP achieves state-of-the-art (improvement up to 69.78%) performance on the global task of retrieval and yields a substantial 3.2% improvement in Top-1 accuracy on the region task of bounding-box classification, consistently outperforming prior approaches while providing a balanced, efficient, and plug-and-play solution to the global-local trade-off in CLIP. Code is available at https://github.com/Erosist/HarmoCLIP.
title HarmoCLIP: Harmonizing Global and Regional Representations in Contrastive Vision-Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.22594