Open-Attribute Recognition for Person Retrieval: Finding People Through Distinctive and Novel Attributes

TL;DR

This paper introduces the Open-Attribute Recognition for Person Retrieval (OAPR) task, enabling retrieval based on both seen and unseen attributes, and proposes a framework for generalizable attribute learning to improve person identification.

Contribution

It defines the new OAPR task and develops a framework for learning generalizable body part representations that handle novel attributes in person retrieval.

Findings

OAPR is necessary for real-world person retrieval scenarios.

The proposed framework effectively recognizes both seen and unseen attributes.

Experimental results demonstrate improved retrieval performance with the new approach.

Abstract

Pedestrian Attribute Recognition (PAR) plays a crucial role in various vision tasks such as person retrieval and identification. Most existing attribute-based retrieval methods operate under the closed-set assumption that all attribute classes are consistently available during both training and inference. However, this assumption limits their applicability in real-world scenarios where novel attributes may emerge. Moreover, predefined attributes in benchmark datasets are often generic and shared across individuals, making them less discriminative for retrieving the target person. To address these challenges, we propose the Open-Attribute Recognition for Person Retrieval (OAPR) task, which aims to retrieve individuals based on attribute cues, regardless of whether those attributes were seen during training. To support this task, we introduce a novel framework designed to learn generalizable body part representations that cover a broad range of attribute categories. Furthermore, we reconstruct four widely used datasets for open-attribute recognition. Comprehensive experiments on these datasets demonstrate the necessity of the OAPR task and the effectiveness of our framework. The source code and pre-trained models will be publicly available upon publication.