Unsupervised Person Re-identification by Soft Multilabel Learning

TL;DR

This paper introduces a novel deep learning approach for unsupervised person re-identification that leverages soft multilabels, cross-view consistency, and reference agents to improve discriminative feature learning without pairwise labels.

Contribution

It proposes a soft multilabel learning framework with cross-view consistency and reference agent representation for unsupervised RE-ID, outperforming existing methods.

Findings

Outperforms state-of-the-art unsupervised RE-ID methods on Market-1501 and DukeMTMC-reID datasets.

Introduces soft multilabel-guided hard negative mining for better discriminative features.

Develops cross-view consistent soft multilabel learning to handle cross-camera variations.

Abstract

Although unsupervised person re-identification (RE-ID) has drawn increasing research attentions due to its potential to address the scalability problem of supervised RE-ID models, it is very challenging to learn discriminative information in the absence of pairwise labels across disjoint camera views. To overcome this problem, we propose a deep model for the soft multilabel learning for unsupervised RE-ID. The idea is to learn a soft multilabel (real-valued label likelihood vector) for each unlabeled person by comparing (and representing) the unlabeled person with a set of known reference persons from an auxiliary domain. We propose the soft multilabel-guided hard negative mining to learn a discriminative embedding for the unlabeled target domain by exploring the similarity consistency of the visual features and the soft multilabels of unlabeled target pairs. Since most target pairs are cross-view pairs, we develop the cross-view consistent soft multilabel learning to achieve the learning goal that the soft multilabels are consistently good across different camera views. To enable effecient soft multilabel learning, we introduce the reference agent learning to represent each reference person by a reference agent in a joint embedding. We evaluate our unified deep model on Market-1501 and DukeMTMC-reID. Our model outperforms the state-of-the-art unsupervised RE-ID methods by clear margins. Code is available at https://github.com/KovenYu/MAR.