Confidence-Guided Centroids for Unsupervised Person Re-Identification

doi:10.1109/TIFS.2024.3414310

Confidence-Guided Centroids for Unsupervised Person Re-Identification

2024-01-01

1

OA

AI

DOI：10.1109/TIFS.2024.3414310

Original

Original request for help

Save

Abstract

En 中文

Unsupervised person re-identification (ReID) aims to train a feature extractor for identity retrieval without exploiting identity labels. Due to the no-reference trust in imperfect clustering results, the learning is inevitably misled by unreliable pseudo labels. Albeit the pseudo label refinement has been investigated by previous works, they generally leverage auxiliary information such as camera IDs and body part predictions. This work explores the internal characteristics of clusters to refine pseudo labels. To this end, Confidence-Guided Centroids (CGC) are proposed to provide reliable cluster-wise prototypes for feature learning. Since samples with high confidence are exclusively involved in the formation of centroids, the identity information of low-confidence samples, i.e., boundary samples, are NOT likely to contribute to the corresponding centroid. Given the new centroids, the current learning scheme, where samples are forced to learn from their assigned centroids solely, is unwise. To remedy the situation, we propose to use Confidence-Guided pseudo Label (CGL), which enables samples to approach not only the originally assigned centroid but also other centroids that are potentially embedded with their identity information. Empowered by confidence-guided centroids and labels, our method yields comparable performance with, or even outperforms, state-of-the-art pseudo label refinement works that largely leverage auxiliary information.

Keywords:

Training

Reliability

Representation learning

Noise

Visualization

Cameras

Prototypes

Person re-identification

unsupervised learning

centroid

visual surveillance

Confidence-Guided Centroids for Unsupervised Person Re-Identification

Abstract

Journal

Organization