• Home
  • Search
  • Progressive Unsupervised Domain Adaptation for Image-based Person Re-Identification
  • Cite Icon3
  • https://doi.org/10.1109/icpr48806.2021.9413291Copy DOI Icon

Progressive Unsupervised Domain Adaptation for Image-based Person Re-Identification

  • Jan 10, 2021
  • Mingliang Yang +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Unsupervised domain adaptation (UDA) has emerged as an effective paradigm for reducing the huge manual annotation cost for Person Re-Identification (Re-ID). Many of the recent UDA methods for Re-ID are clustering-based and select all the pseudo-label samples in each iteration for the model training. However, there are many wrong labeled samples that will mislead the model optimization under this circumstance. To solve this problem, we propose a Progressive Unsupervised Domain Adaptation (PUDA) framework for image-based Person Re-ID to reduce the negative effect of wrong pseudo-label samples on the model training process. Specifically, we first pretrain a CNN model on a labeled source dataset, then finetune the model on unlabeled target dataset with the following three steps iteratively: 1) estimating pseudo-labels for all the images in the target dataset with the model trained in the last iteration; 2) extending the training set by adding pseudo-label samples with higher label confidence; 3) updating the CNN model with the expanded training set in a supervised manner. During the iteration process, the number of pseudo-label samples added increased progressively. In particular, a Moderate Initial Selections (MIS) strategy for pseudo-label sampling is also proposed to reduce the negative impacts of random noise features in the early iterations and mislabeled samples in the late iterations on the model. The proposed framework with MIS strategy is validated on the Duke-to-Market, Market-to-Duke unsupervised domain adaptation tasks and achieves improvements of 4.2 points (absolute, i.e., 80.0% vs. 75.8%) and 1.7 points (absolute, i.e., 70.7% vs. 69.0%) in mAP correspondingly.

Similar Papers
  • Video Transcripts

Progressive Unsupervised Domain Adaptation for Image-based Person Re-Identification

  • Dec 29, 2020
  • Underline Science Inc.
  • Mingliang Yang
  • Research Article
  • Citations2

Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification

  • Jul 14, 2025
  • PLOS One
  • Xuemei Bai +3
  • Research Article
  • Citations6

Semantically preserving adversarial unsupervised domain adaptation network for improving disease recognition from chest x-rays.

  • Jul 01, 2023
  • Computerized Medical Imaging and Graphics
  • Xiaoli Qin +2
  • Research Article
  • Citations3

An Unsupervised Domain Adaption Approach for Cross-Modality RGB-Infrared Person Re-Identification

  • Dec 15, 2023
  • IEEE Sensors Journal
  • Qingshan Chen +4
  • Research Article
  • Citations6

Cross-Domain Urban Land Use Classification via Scenewise Unsupervised Multisource Domain Adaptation With Transformer

  • Jan 01, 2024
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Mengmeng Li +3
  • Research Article
  • Citations1

Unsupervised Person Re-Identification via Deep Attribute Learning

  • Aug 15, 2025
  • Future Internet
  • Shun Zhang +4
  • Conference Article
  • Citations13

Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-Identification

  • Oct 16, 2022
  • Félix Remigereau +5
  • Research Article
  • Citations10

Cryo-shift: reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization.

  • Nov 23, 2021
  • Bioinformatics
  • Hmrishav Bandyopadhyay +7
  • Conference Article
  • Citations4

Self-Supervised Person Re-Identification with Channel-Wise Transformer

  • Dec 17, 2022
  • Zian Ye +3
  • Research Article
  • Citations7

A Camera Identity-guided Distribution Consistency Method for Unsupervised Multi-target Domain Person Re-identification

  • Jun 08, 2021
  • ACM Transactions on Intelligent Systems and Technology
  • Jiajie Tian +5
  • Research Article
  • Citations5

Unsupervised Domain Adaptation on Person Reidentification Via Dual-Level Asymmetric Mutual Learning.

  • Jan 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Qiong Wu +6
  • Research Article
  • Citations2

Rainforest: A three-stage distribution adaptation framework for unsupervised time series domain adaptation

  • Aug 30, 2024
  • Neurocomputing
  • Yingyi Zhong +1
  • Research Article
  • Citations27

Generative Self-training for Cross-domain Unsupervised Tagged-to-Cine MRI Synthesis.

  • Jan 01, 2021
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
  • Xiaofeng Liu +7
  • Conference Article
  • Citations4

Learn by Guessing: Multi-step Pseudo-label Refinement for Person Re-Identification

  • Jan 01, 2022
  • Tiago Pereira +1
  • Conference Article
  • Citations5

Unsupervised Domain Adaptation with Histogram-gated Image Translation for Delayered IC Image Analysis

  • Oct 25, 2022
  • Yee-Yang Tee +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.