Generalizable Person Re-identification
5 papers with code • 6 benchmarks • 3 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
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Market-1501
DukeMTMC-reID
Greatest papers with code
Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification
Then, each mini batch is composed of a randomly selected class and its nearest neighboring classes so as to provide informative and challenging examples for learning.
Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting
shengcailiao/QAConv
•
•
ECCV 2020
In this paper, beyond representation learning, we consider how to formulate person image matching directly in deep feature maps.
Domain Generalization
Generalizable Person Re-identification
+1
Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification
To address this, we propose to automatically synthesize a large-scale person re-identification dataset following a set-up similar to real surveillance but with virtual environments, and then use the synthesized person images to train a generalizable person re-identification model.
Domain Generalization
Generalizable Person Re-identification
+1
Meta Batch-Instance Normalization for Generalizable Person Re-Identification
bismex/MetaBIN
•
•
To this end, we combine learnable batch-instance normalization layers with meta-learning and investigate the challenging cases caused by both batch and instance normalization layers.
Dual Distribution Alignment Network for Generalizable Person Re-Identification
Pealing/DDAN
•
•
Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID), which trains the model using labels from the source domain alone, and then directly adopts the trained model to the target domain without model updating.
Domain Generalization
Generalizable Person Re-identification