Browse > Computer Vision > Person Re-Identification > Unsupervised Person Re-Identification

Unsupervised Person Re-Identification

12 papers with code · Computer Vision

Leaderboards

Greatest papers with code

Learning Generalisable Omni-Scale Representations for Person Re-Identification

15 Oct 2019KaiyangZhou/deep-person-reid

An effective person re-identification (re-ID) model should learn feature representations that are both discriminative, for distinguishing similar-looking people, and generalisable, for deployment across datasets without any adaptation.

UNSUPERVISED DOMAIN ADAPTATION UNSUPERVISED PERSON RE-IDENTIFICATION

Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns

CVPR 2018 ahangchen/TFusion

Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to poor performance due to underfitting.

LEARNING-TO-RANK TRANSFER LEARNING UNSUPERVISED PERSON RE-IDENTIFICATION

Unsupervised Person Re-identification by Soft Multilabel Learning

CVPR 2019 KovenYu/MAR

To overcome this problem, we propose a deep model for the soft multilabel learning for unsupervised RE-ID.

UNSUPERVISED PERSON RE-IDENTIFICATION

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

ICLR 2020 yxgeee/MMT

In order to mitigate the effects of noisy pseudo labels, we propose to softly refine the pseudo labels in the target domain by proposing an unsupervised framework, Mutual Mean-Teaching (MMT), to learn better features from the target domain via off-line refined hard pseudo labels and on-line refined soft pseudo labels in an alternative training manner.

UNSUPERVISED DOMAIN ADAPTATION UNSUPERVISED PERSON RE-IDENTIFICATION

Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification

ICCV 2019 OasisYang/SSG

Upon our SSG, we further introduce a clustering-guided semisupervised approach named SSG ++ to conduct the one-shot domain adaption in an open set setting (i. e. the number of independent identities from the target domain is unknown).

ONE-SHOT LEARNING UNSUPERVISED DOMAIN ADAPTATION UNSUPERVISED PERSON RE-IDENTIFICATION

Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification

CVPR 2019 QizeYang/PAUL

Specifically, we develop a PatchNet to select patches from the feature map and learn discriminative features for these patches.

UNSUPERVISED PERSON RE-IDENTIFICATION

Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification

4 Jun 2019gddingcs/Dispersion-based-Clustering

With this insight, we design a novel Dispersion-based Clustering (DBC) approach which can discover the underlying patterns in data.

UNSUPERVISED PERSON RE-IDENTIFICATION

Adaptive Exploration for Unsupervised Person Re-Identification

9 Jul 2019dyh127/Adaptive-Exploration-for-Unsupervised-Person-Re-Identification

However, a problem of the adaptive selection is that, when an image has too many neighborhoods, it is more likely to attract other images as its neighborhoods.

UNSUPERVISED PERSON RE-IDENTIFICATION

Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification

ICCV 2017 KovenYu/CAMEL

While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires quantities of labeled samples in all pairs of camera views for training.

METRIC LEARNING UNSUPERVISED PERSON RE-IDENTIFICATION