Unsupervised Person Re-Identification
Leaderboards
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Greatest papers with code
Learning Generalisable Omni-Scale Representations for Person Re-Identification
• KaiyangZhou/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.
#38 best model for
Person Re-Identification
on DukeMTMC-reID
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.
SOTA for Unsupervised Person Re-Identification on DukeMTMC-reID->Market-1501 (mAP metric )
UNSUPERVISED DOMAIN ADAPTATION UNSUPERVISED PERSON RE-IDENTIFICATION
Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
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
Specifically, we develop a PatchNet to select patches from the feature map and learn discriminative features for these patches.
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.
FACE RECOGNITION PERSON IDENTIFICATION ROBUST FACE RECOGNITION UNSUPERVISED PERSON RE-IDENTIFICATION
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.
#3 best model for
Unsupervised Person Re-Identification
on Market-1501
Adaptive Exploration for Unsupervised Person Re-Identification
• dyh127/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.
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.
#55 best model for
Person Re-Identification
on Market-1501