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 with no code
Generalizable Person Re-Identification via Viewpoint Alignment and Fusion
The key insight of this design is that the cross-attention mechanism in the transformer could be an ideal solution to align the discriminative texture clues from the original image with the canonical view image, which could compensate for the low-quality texture information of the canonical view image.
Generalizable Re-Identification from Videos with Cycle Association
In this paper, we are interested in learning a generalizable person re-identification (re-ID) representation from unlabeled videos.
Towards Generalizable Person Re-identification with a Bi-stream Generative Model
Guided by original pedestrian images, one stream is employed to learn a camera-invariant global feature for the CC problem via filtering cross-camera interference factors.
Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification
In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization.
Generalizable Person Re-Identification via Self-Supervised Batch Norm Test-Time Adaption
In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain.
TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification
In the meantime, we design an adaptive BN layer in the domain-invariant stream, to approximate the statistics of various unseen domains.
Generalizable Person Re-identification Without Demographics
However, the convex condition of KL DRO may not hold for overparameterized neural networks, such that applying KL DRO often fails to generalize under distribution shifts in real scenarios.
Domain-Class Correlation Decomposition for Generalizable Person Re-Identification
Domain adversarial learning is a promising domain generalization method that aims to remove domain information in the latent representation through adversarial training.
Generalizable Person Re-identification with Relevance-aware Mixture of Experts
Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics.
Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification
It describes unseen target domain as a combination of the known source ones, and explicitly learns domain-specific representation with target distribution to improve the model's generalization by a meta-learning pipeline.
