Unsupervised Tracklet Person Re-Identification

TL;DR

This paper introduces an unsupervised deep learning framework for person re-identification that automatically discovers discriminative features from tracklet data, eliminating the need for manual labeling and improving scalability.

Contribution

It proposes the UTAL framework that jointly learns within-camera discrimination and cross-camera association in an end-to-end manner, advancing unsupervised re-id methods.

Findings

Outperforms state-of-the-art unsupervised re-id methods on multiple datasets.

Effectively discovers discriminative features without manual labels.

Demonstrates robustness across eight benchmark datasets.

Abstract

Most existing person re-identification (re-id) methods rely on supervised model learning on per-camera-pair manually labelled pairwise training data. This leads to poor scalability in a practical re-id deployment, due to the lack of exhaustive identity labelling of positive and negative image pairs for every camera-pair. In this work, we present an unsupervised re-id deep learning approach. It is capable of incrementally discovering and exploiting the underlying re-id discriminative information from automatically generated person tracklet data end-to-end. We formulate an Unsupervised Tracklet Association Learning (UTAL) framework. This is by jointly learning within-camera tracklet discrimination and cross-camera tracklet association in order to maximise the discovery of tracklet identity matching both within and across camera views. Extensive experiments demonstrate the superiority of the proposed model over the state-of-the-art unsupervised learning and domain adaptation person re-id methods on eight benchmarking datasets.