Unsupervised Person Re-Identification

58 papers with code • 19 benchmarks • 11 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Joint Discriminative and Generative Learning for Person Re-identification

layumi/Person_reID_baseline_pytorch CVPR 2019

To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end.

Learning Generalisable Omni-Scale Representations for Person Re-Identification

KaiyangZhou/deep-person-reid 15 Oct 2019

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.

Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID

yxgeee/VisDA-ECCV20 14 Mar 2020

To tackle the challenges, we propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term.

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

yxgeee/SpCL NeurIPS 2020

To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory.

Cluster Contrast for Unsupervised Person Re-Identification

alibaba/cluster-contrast 22 Mar 2021

Thus, our method can solve the problem of cluster inconsistency and be applicable to larger data sets.

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

yxgeee/MMT ICLR 2020

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.

Weakly supervised discriminative feature learning with state information for person identification

KovenYu/state-information CVPR 2020

We evaluate our model on unsupervised person re-identification and pose-invariant face recognition.

Rethinking Sampling Strategies for Unsupervised Person Re-identification

ucas-vg/groupsampling 7 Jul 2021

While extensive research has focused on the framework design and loss function, this paper shows that sampling strategy plays an equally important role.

Unsupervised Person Re-identification with Stochastic Training Strategy

lithium770/unsupervised-person-re-id-with-stochastic-training-strategy 16 Aug 2021

State-of-the-art unsupervised re-ID methods usually follow a clustering-based strategy, which generates pseudo labels by clustering and maintains a memory to store instance features and represent the centroid of the clusters for contrastive learning.