• Home
  • Search
  • Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding.
  • Open Access IconOpen Access
  • Cite Icon192
  • https://doi.org/10.1109/tpami.2018.2886878Copy DOI Icon

Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Person re-identification (Re-ID) aims to match identities across non-overlapping camera views. Researchers have proposed many supervised Re-ID models which require quantities of cross-view pairwise labelled data. This limits their scalabilities to many applications where a large amount of data from multiple disjoint camera views is available but unlabelled. Although some unsupervised Re-ID models have been proposed to address the scalability problem, they often suffer from the view-specific bias problem which is caused by dramatic variances across different camera views, e.g., different illumination, viewpoints and occlusion. The dramatic variances induce specific feature distortions in different camera views, which can be very disturbing in finding cross-view discriminative information for Re-ID in the unsupervised scenarios, since no label information is available to help alleviate the bias. We propose to explicitly address this problem by learning an unsupervised asymmetric distance metric based on cross-view clustering. The asymmetric distance metric allows specific feature transformations for each camera view to tackle the specific feature distortions. We then design a novel unsupervised loss function to embed the asymmetric metric into a deep neural network, and therefore develop a novel unsupervised deep framework named the DEep Clustering-based Asymmetric MEtric Learning (DECAMEL). In such a way, DECAMEL jointly learns the feature representation and the unsupervised asymmetric metric. DECAMEL learns a compact cross-view cluster structure of Re-ID data, and thus help alleviate the view-specific bias and facilitate mining the potential cross-view discriminative information for unsupervised Re-ID. Extensive experiments on seven benchmark datasets whose sizes span several orders show the effectiveness of our framework.

Similar Papers
  • Research Article
  • Citations3

Asymmetric person re-identification: cross-view person tracking in a large camera network

  • May 01, 2018
  • SCIENTIA SINICA Informationis
  • Ancong Wu +1
  • Conference Article
  • Citations388

Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification

  • Oct 01, 2017
  • Hong-Xing Yu +2
  • Research Article
  • Citations9

Imitating targets from all sides: an unsupervised transfer learning method for person re-identification

  • Apr 02, 2021
  • International Journal of Machine Learning and Cybernetics
  • Jiajie Tian +4
  • Research Article
  • Citations14

A Versatile Framework for Multi-Scene Person Re-Identification.

  • Mar 01, 2025
  • IEEE transactions on pattern analysis and machine intelligence
  • Wei-Shi Zheng +2
  • Conference Article
  • Citations453

Unsupervised Person Re-Identification by Soft Multilabel Learning

  • Jun 01, 2019
  • Hong-Xing Yu +5
  • Conference Article
  • Citations7

Optimizing Federated Unsupervised Person Re-identification via Camera-aware Clustering

  • Sep 26, 2022
  • Jiabei Liu +4
  • Research Article
  • Citations8

Unsupervised Learning of Intrinsic Semantics with Diffusion Model for Person Re-Identification.

  • Jan 01, 2024
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Xuefeng Tao +4
  • Research Article

Protecting Feature Privacy in Person Re-Identification.

  • Jan 01, 2025
  • IEEE transactions on pattern analysis and machine intelligence
  • Xiao Li +2
  • Research Article
  • Citations39

Progressive Unsupervised Person Re-Identification by Tracklet Association With Spatio-Temporal Regularization

  • Mar 27, 2020
  • IEEE Transactions on Multimedia
  • Qiaokang Xie +4
  • Conference Article
  • Citations143

Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency Learning

  • Oct 01, 2019
  • Ancong Wu +2
  • Research Article
  • Citations88

Cross-Scenario Transfer Person Reidentification

  • Aug 01, 2016
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Xiaojuan Wang +3
  • Book Chapter
  • Citations74

Global Distance-Distributions Separation for Unsupervised Person Re-identification

  • Jan 01, 2020
  • Xin Jin +3
  • Research Article

Camera Style Alignment for Unsupervised Person Re-Identification

  • Jan 01, 2025
  • IEICE Transactions on Information and Systems
  • Jifeng Guo +4
  • Research Article

Negative Semantic Guided Identity Boundary Construction for Open-World Person Re-Identification

  • Jan 01, 2026
  • IEEE Transactions on Multimedia
  • Xiao-Wen Zhang +4
  • Conference Article
  • Citations127

Distilled Person Re-Identification: Towards a More Scalable System

  • Jun 01, 2019
  • Ancong Wu +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.