Unsupervised Person Re-Identification
58 papers with code • 19 benchmarks • 11 datasets
Benchmarks
These leaderboards are used to track progress in Unsupervised Person Re-Identification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Datasets
Market-1501
DukeMTMC-reID
MSMT17
MARS
DukeMTMC-VideoReID
iLIDS-VID
Latest papers
SimMC: Simple Masked Contrastive Learning of Skeleton Representations for Unsupervised Person Re-Identification
kali-hac/simmc
•
•
Specifically, to fully exploit skeleton features within each skeleton sequence, we first devise a masked prototype contrastive learning (MPC) scheme to cluster the most typical skeleton features (skeleton prototypes) from different subsequences randomly masked from raw sequences, and contrast the inherent similarity between skeleton features and different prototypes to learn discriminative skeleton representations without using any label.
Implicit Sample Extension for Unsupervised Person Re-Identification
PaddlePaddle/PaddleClas
•
•
CVPR 2022
Specifically, we generate support samples from actual samples and their neighbouring clusters in the embedding space through a progressive linear interpolation (PLI) strategy.
Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification
shengcailiao/QAConv
•
•
CVPR 2022
To address this, in this work, an automatic approach is proposed to directly clone the whole outfits from real-world person images to virtual 3D characters, such that any virtual person thus created will appear very similar to its real-world counterpart.
Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
In this paper, we propose a novel Part-based Pseudo Label Refinement (PPLR) framework that reduces the label noise by employing the complementary relationship between global and part features.
Unsupervised Lifelong Person Re-identification via Contrastive Rehearsal
chenhao2345/ucr
•
•
Existing unsupervised person re-identification (ReID) methods focus on adapting a model trained on a source domain to a fixed target domain.
Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution
Gabrielcb/Leveraging_ensembles_and_self_supervised_fully_ReID
•
•
We propose a strategy to tackle Person Re-Identification and Text Authorship Attribution by enabling learning from unlabeled data even when samples from different classes are not prominently diverse.
Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification
Assisted with the camera-aware proxies, we design two proxy-level contrastive learning losses that are, respectively, based on offline and online association results.
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks.
Exploiting Robust Unsupervised Video Person Re-identification
deropty/uPMnet
•
•
A local-aware module is employed to explore the poentials of local-level feature for unsupervised learning.
Unsupervised Person Re-Identification with Wireless Positioning under Weak Scene Labeling
To this end, we propose to explore unsupervised person re-identification with both visual data and wireless positioning trajectories under weak scene labeling, in which we only need to know the locations of the cameras.
