Unsupervised Domain Adaptive Re-Identification: Theory and Practice

Liangchen Song, Cheng Wang, Lefei Zhang, Bo Du, Qian Zhang +2 more
7/30/2018
cs.CV

Official code: lsongx/DomainAdaptiveReID (187 stars, MIT, last commit 2019-01-16).

Abstract

We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation. We first extend existing unsupervised domain adaptive classification theories to re-ID tasks. Concretely, we introduce some assumptions on the extracted feature space and then derive several loss functions guided by these assumptions. To optimize them, a novel self-training scheme for unsupervised domain adaptive re-ID tasks is proposed. It iteratively makes guesses for unlabeled target data based on an encoder and trains the encoder based on the guessed labels. Extensive experiments on unsupervised domain adaptive person re-ID and vehicle re-ID tasks with comparisons to the state-of-the-arts confirm the effectiveness of the proposed theories and self-training framework. Our code is available at \url{https://github.com/LcDog/DomainAdaptiveReID}.

View on arXivView PDF

Code Implementations(1)

lsongx/DomainAdaptiveReIDOfficial100%
MIT
18750Python, Jupyter NotebookJul 28, 20187 years agoMIT

Similar Papers

Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification

87% match1 repo3042019

Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification

86% match1 repo102023

Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

86% match1 repo4792020

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

84% match1 repo1022021

Semi-Supervised Domain Generalizable Person Re-Identification

84% match1 repo4.0k2021

Pose-Transformation and Radial Distance Clustering for Unsupervised Person Re-identification

83% match2024

Cite this paper

@article{song2018unsupervised,
  title  = {Unsupervised Domain Adaptive Re-Identification: Theory and Practice},
  author = {Liangchen Song and Cheng Wang and Lefei Zhang and Bo Du and Qian Zhang and Chang Huang and Xinggang Wang},
  year   = {2018},
  eprint = {1807.11334},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1807.11334}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1807.11334.svg)](https://codeofpaper.com/paper/1807.11334)

Discussion