X-ReID: Cross-Instance Transformer for Identity-Level Person Re-Identification

Currently, most existing person re-identification methods use instance-level features, which are extracted only from a single image. However, these instance-level features can easily ignore the discriminative information because the appearance of each identity varies greatly in different images. Thu...

Full description

Saved in:
Bibliographic Details
Main Authors: Shen, Leqi, He, Tao, Zhao, Sicheng, Shen, Zhelun, Guo, Yuchen, Xu, Tianshi, Ding, Guiguang
Format: Conference Proceeding
Language:English
Subjects:
Benchmark testing
Cross-attention
Data mining
Feature extraction
Identification of persons
Identity-level
Image classification
Pedestrians
Person Re-Identification
Training
Transformer
Transformers
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Currently, most existing person re-identification methods use instance-level features, which are extracted only from a single image. However, these instance-level features can easily ignore the discriminative information because the appearance of each identity varies greatly in different images. Thus, it is necessary to exploit identity-level features, which can be shared across different images of each identity. In this paper, we propose a novel training framework, named X-ReID, to promote instance-level features to identity-level features by employing cross-attention to incorporate information from one image to another of the same identity, thus more unified and discriminative pedestrian information can be obtained. Extensive experiments on benchmark datasets show the superiority of our method over existing works. Particularly, on the challenging MSMT17, our proposed method gains 1.1% mAP improvements when compared to the second place.
ISSN:1945-788X
DOI:10.1109/ICME57554.2024.10687457