Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zheng, Tianlu, Zhang, Yifan, An, Xiang, Feng, Ziyong, Yang, Kaicheng, Ding, Qichuan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912581854167040
author Zheng, Tianlu
Zhang, Yifan
An, Xiang
Feng, Ziyong
Yang, Kaicheng
Ding, Qichuan
author_facet Zheng, Tianlu
Zhang, Yifan
An, Xiang
Feng, Ziyong
Yang, Kaicheng
Ding, Qichuan
contents Although Contrastive Language-Image Pre-training (CLIP) exhibits strong performance across diverse vision tasks, its application to person representation learning faces two critical challenges: (i) the scarcity of large-scale annotated vision-language data focused on person-centric images, and (ii) the inherent limitations of global contrastive learning, which struggles to maintain discriminative local features crucial for fine-grained matching while remaining vulnerable to noisy text tokens. This work advances CLIP for person representation learning through synergistic improvements in data curation and model architecture. First, we develop a noise-resistant data construction pipeline that leverages the in-context learning capabilities of MLLMs to automatically filter and caption web-sourced images. This yields WebPerson, a large-scale dataset of 5M high-quality person-centric image-text pairs. Second, we introduce the GA-DMS (Gradient-Attention Guided Dual-Masking Synergetic) framework, which improves cross-modal alignment by adaptively masking noisy textual tokens based on the gradient-attention similarity score. Additionally, we incorporate masked token prediction objectives that compel the model to predict informative text tokens, enhancing fine-grained semantic representation learning. Extensive experiments show that GA-DMS achieves state-of-the-art performance across multiple benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09118
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
Zheng, Tianlu
Zhang, Yifan
An, Xiang
Feng, Ziyong
Yang, Kaicheng
Ding, Qichuan
Computer Vision and Pattern Recognition
Although Contrastive Language-Image Pre-training (CLIP) exhibits strong performance across diverse vision tasks, its application to person representation learning faces two critical challenges: (i) the scarcity of large-scale annotated vision-language data focused on person-centric images, and (ii) the inherent limitations of global contrastive learning, which struggles to maintain discriminative local features crucial for fine-grained matching while remaining vulnerable to noisy text tokens. This work advances CLIP for person representation learning through synergistic improvements in data curation and model architecture. First, we develop a noise-resistant data construction pipeline that leverages the in-context learning capabilities of MLLMs to automatically filter and caption web-sourced images. This yields WebPerson, a large-scale dataset of 5M high-quality person-centric image-text pairs. Second, we introduce the GA-DMS (Gradient-Attention Guided Dual-Masking Synergetic) framework, which improves cross-modal alignment by adaptively masking noisy textual tokens based on the gradient-attention similarity score. Additionally, we incorporate masked token prediction objectives that compel the model to predict informative text tokens, enhancing fine-grained semantic representation learning. Extensive experiments show that GA-DMS achieves state-of-the-art performance across multiple benchmarks.
title Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.09118