Unsupervised Person Re-Identification
51 papers with code • 15 benchmarks • 8 datasets
These leaderboards are used to track progress in Unsupervised Person Re-Identification
Most implemented papers
Joint Discriminative and Generative Learning for Person Re-identification
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
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
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
To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory.
Cluster Contrast for Unsupervised Person Re-Identification
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
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
We evaluate our model on unsupervised person re-identification and pose-invariant face recognition.
Joint Generative and Contrastive Learning for Unsupervised Person Re-identification
In this context, we propose a mesh-based view generator.
Rethinking Sampling Strategies for Unsupervised Person Re-identification
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
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.