Progressive Unsupervised Person Re-identification by Tracklet Association with Spatio-Temporal Regularization

TL;DR

This paper introduces a progressive unsupervised person re-identification method that leverages tracklet association and spatio-temporal regularization to improve cross-camera person matching without manual labels.

Contribution

It proposes a novel iterative framework that progressively refines the Re-ID model using automatic tracklet association and spatio-temporal constraints, eliminating the need for manual annotations.

Findings

Achieves effective unsupervised person Re-ID in real-world scenarios.

Outperforms existing unsupervised methods on benchmark datasets.

Demonstrates the benefit of iterative refinement with tracklet association.

Abstract

Existing methods for person re-identification (Re-ID) are mostly based on supervised learning which requires numerous manually labeled samples across all camera views for training. Such a paradigm suffers the scalability issue since in real-world Re-ID application, it is difficult to exhaustively label abundant identities over multiple disjoint camera views. To this end, we propose a progressive deep learning method for unsupervised person Re-ID in the wild by Tracklet Association with Spatio-Temporal Regularization (TASTR). In our approach, we first collect tracklet data within each camera by automatic person detection and tracking. Then, an initial Re-ID model is trained based on within-camera triplet construction for person representation learning. After that, based on the person visual feature and spatio-temporal constraint, we associate cross-camera tracklets to generate cross-camera triplets and update the Re-ID model. Lastly, with the refined Re-ID model, better visual feature of person can be extracted, which further promote the association of cross-camera tracklets. The last two steps are iterated multiple times to progressively upgrade the Re-ID model.