Harnessing Weak Pair Uncertainty for Text-based Person Search

TL;DR

This paper proposes an uncertainty-aware approach for text-based person search that leverages weak positive pairs, improving retrieval accuracy by explicitly modeling pair uncertainty.

Contribution

It introduces a novel uncertainty estimation and regularization framework to better utilize weak positive pairs in text-based person search.

Findings

Achieves +3.06%, +3.55%, +6.94% mAP improvements on three datasets.

Explicitly models pair uncertainty to enhance retrieval performance.

Incorporates group-wise matching loss for better representation learning.

Abstract

In this paper, we study the text-based person search, which is to retrieve the person of interest via natural language description. Prevailing methods usually focus on the strict one-to-one correspondence pair matching between the visual and textual modality, such as contrastive learning. However, such a paradigm unintentionally disregards the weak positive image-text pairs, which are of the same person but the text descriptions are annotated from different views (cameras). To take full use of weak positives, we introduce an uncertainty-aware method to explicitly estimate image-text pair uncertainty, and incorporate the uncertainty into the optimization procedure in a smooth manner. Specifically, our method contains two modules: uncertainty estimation and uncertainty regularization. (1) Uncertainty estimation is to obtain the relative confidence on the given positive pairs; (2) Based on the predicted uncertainty, we propose the uncertainty regularization to adaptively adjust loss weight. Additionally, we introduce a group-wise image-text matching loss to further facilitate the representation space among the weak pairs. Compared with existing methods, the proposed method explicitly prevents the model from pushing away potentially weak positive candidates. Extensive experiments on three widely-used datasets, .e.g, CUHK-PEDES, RSTPReid and ICFG-PEDES, verify the mAP improvement of our method against existing competitive methods +3.06%, +3.55% and +6.94%, respectively.