Generalizable Person Re-identification
21 papers with code • 4 benchmarks • 9 datasets
Generalizable person re-identification refers to methods trained on a source dataset but directly evaluated on a target dataset without domain adaptation or transfer learning.
Benchmarks
These leaderboards are used to track progress in Generalizable Person Re-identification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Market-1501
CUHK03
MSMT17
Market-1501-C
ClonedPerson
Latest papers
Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification
dcp15/isr_iccv2023_oral
•
•
ICCV 2023
To overcome the barriers of data and annotation, we propose to utilize large-scale unsupervised data for training.
Part-Aware Transformer for Generalizable Person Re-identification
liyuke65535/part-aware-transformer
•
•
ICCV 2023
Based on the local similarity obtained in CSL, a Part-guided Self-Distillation (PSD) is proposed to further improve the generalization of global features.
Learning Robust Visual-Semantic Embedding for Generalizable Person Re-identification
jeremyxsc/mmet
•
•
In this paper, we propose a Multi-Modal Equivalent Transformer called MMET for more robust visual-semantic embedding learning on visual, textual and visual-textual tasks respectively.
Deep Multimodal Fusion for Generalizable Person Re-identification
jeremyxsc/dmf
•
•
Person re-identification plays a significant role in realistic scenarios due to its various applications in public security and video surveillance.
Is Synthetic Dataset Reliable for Benchmarking Generalizable Person Re-Identification?
Through the designed pairwise ranking analysis and comprehensive evaluations, we conclude that a recent large-scale synthetic dataset ClonedPerson can be reliably used to benchmark GPReID, statistically the same as real-world datasets.
Style Variable and Irrelevant Learning for Generalizable Person Re-identification
hbchen121/dgreid
•
•
In this paper, we first verify through an experiment that style factors are a vital part of domain bias.
Style Interleaved Learning for Generalizable Person Re-identification
wentaotan/interleaved-learning
•
•
This common practice causes the model to overfit to existing feature styles in the source domain, resulting in sub-optimal generalization ability on target domains.
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.
Meta Distribution Alignment for Generalizable Person Re-Identification
Domain Generalizable (DG) person ReID is a challenging task which trains a model on source domains yet generalizes well on target domains.
Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification
xbq1994/meta
•
•
Meanwhile, META considers the relevance of an unseen target sample and source domains via normalization statistics and develops an aggregation module to adaptively integrate multiple experts for mimicking unseen target domain.
