Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification

TL;DR

This paper introduces TJ-AIDL, a deep learning model that transfers attribute and identity information from labeled datasets to new, unlabeled domains for person re-identification, eliminating the need for target domain labels.

Contribution

The novel TJ-AIDL method enables unsupervised person re-id by transferring learned features to unseen domains without additional labeling, improving scalability.

Findings

Outperforms state-of-the-art methods on multiple benchmarks

Effective in transferring knowledge to unseen domains

No need for labeled data in target domain

Abstract

Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair. This significantly limits their scalability and usability in real-world large scale deployments with the need for performing re-id across many camera views. To address this scalability problem, we develop a novel deep learning method for transferring the labelled information of an existing dataset to a new unseen (unlabelled) target domain for person re-id without any supervised learning in the target domain. Specifically, we introduce an Transferable Joint Attribute-Identity Deep Learning (TJ-AIDL) for simultaneously learning an attribute-semantic and identitydiscriminative feature representation space transferrable to any new (unseen) target domain for re-id tasks without the need for collecting new labelled training data from the target domain (i.e. unsupervised learning in the target domain). Extensive comparative evaluations validate the superiority of this new TJ-AIDL model for unsupervised person re-id over a wide range of state-of-the-art methods on four challenging benchmarks including VIPeR, PRID, Market-1501, and DukeMTMC-ReID.