Unsupervised Person Re-Identification
Leaderboards
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
Greatest papers with code
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.
Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
• 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
Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification
Specifically, we develop a PatchNet to select patches from the feature map and learn discriminative features for these patches.
Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification
• gddingcs/Dispersion-based-Clustering
•
With this insight, we design a novel Dispersion-based Clustering (DBC) approach which can discover the underlying patterns in data.
Adaptive Exploration for Unsupervised Person Re-Identification
• dyh127/Adaptive-Exploration-for-Unsupervised-Person-Re-Identification
•
In the first case, by treating each person image as an individual class, a non-parametric classifier with a feature memory is exploited to encourage person images to move away from each other.
Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding
In such a way, DECAMEL jointly learns the feature representation and the unsupervised asymmetric metric.
Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification
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.
Leveraging Virtual and Real Person for Unsupervised Person Re-identification
For training of deep re-ID model, we divide it into three steps: 1) pre-training a coarse re-ID model by using virtual data; 2) collaborative filtering based positive pair mining from the real data; and 3) fine-tuning of the coarse re-ID model by leveraging the mined positive pairs and virtual data.