Unsupervised Person Re-Identification
58 papers with code • 19 benchmarks • 11 datasets
Datasets
Latest papers
MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification
As a challenging task, unsupervised person ReID aims to match the same identity with query images which does not require any labeled information.
Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification
However, the previous approaches did not fully exploit information of hard samples, simply using cluster centroid or all instances for contrastive learning.
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.
Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identification
We present FedUReID, a federated unsupervised person ReID system to learn person ReID models without any labels while preserving privacy.
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.
Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identification
Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set.
Unsupervised Person Re-identification via Multi-Label Prediction and Classification based on Graph-Structural Insight
The proposed GSMLP and SMLC boost the performance of unsupervised person Re-ID without any pre-labelled dataset.
Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification
To be specific, we propose a novel cluster-level contrastive loss to help the siamese network effectively mine the invariance in feature learning with respect to the cluster structure within and between different data augmentation views, respectively.
ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification
Then, we use similarity scores as soft pseudo labels to enhance the consistency between augmented and original views, which makes our model more robust to augmentation perturbations.
Cluster Contrast for Unsupervised Person Re-Identification
Thus, our method can solve the problem of cluster inconsistency and be applicable to larger data sets.