mlsanityData to 7 Oct 2026

Unsupervised Person Re-identification via Multi-Label Prediction and Classification based on Graph-Structural Insight

arXiv 2106.08798 ↗First posted 16 Jun 2021cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper addresses unsupervised person re-identification (Re-ID) using multi-label prediction and classification based on graph-structural insight. Our method extracts features from person images and produces a graph that consists of the features and a pairwise similarity of them as nodes and edges, respectively. Based on the graph, the proposed graph structure based multi-label prediction (GSMLP) method predicts multi-labels by considering the pairwise similarity and the adjacency node distribution of each node. The multi-labels created by GSMLP are applied to the proposed selective multi-label classification (SMLC) loss. SMLC integrates a hard-sample mining scheme and a multi-label classification. The proposed GSMLP and SMLC boost the performance of unsupervised person Re-ID without any pre-labelled dataset. Experimental results justify the superiority of the proposed method in unsupervised person Re-ID by producing state-of-the-art performance. The source code for this paper is publicly available on 'https://github.com/uknownpioneer/GSMLP-SMLC.git'.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 44 references that are in the map. First posted on arXiv 16 Jun 2021.

Builds on

21 of 44 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  3. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
  4. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  5. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  6. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 211
  7. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  8. 2016Person Re-identification: Past, Present and Futurecited by 180
  9. 2017Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptationcited by 151
  10. 2019Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identificationcited by 133
  11. 2019Learning a Deep ConvNet for Multi-label Classification with Partial Labelscited by 124
  12. 2020Unsupervised Person Re-identification via Multi-label Classificationcited by 107
9 more
  1. 2017Pose-driven Deep Convolutional Model for Person Re-identificationcited by 86
  2. 2020Joint Disentangling and Adaptation for Cross-Domain Person Re-Identificationcited by 83
  3. 2020Unsupervised Person Re-identification via Softened Similarity Learningcited by 75
  4. 2017Unsupervised Person Re-identification: Clustering and Fine-tuningcited by 73
  5. 2018Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identificationcited by 62
  6. 2019Self-training with progressive augmentation for unsupervised cross-domain person re-identificationcited by 54
  7. 2019Unsupervised Person Re-identification by Soft Multilabel Learningcited by 53
  8. 2016Gated Siamese Convolutional Neural Network Architecture for Human Re-Identificationcited by 34
  9. 2020Global Distance-distributions Separation for Unsupervised Person Re-identificationcited by 24

Built on by

Not cited yet.