Generalizable Person Re-identification

12 papers with code • 12 benchmarks • 6 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.

Most implemented papers

Semi-Supervised Domain Generalizable Person Re-Identification

JDAI-CV/fast-reid 11 Aug 2021

Instead, we aim to explore multiple labeled datasets to learn generalized domain-invariant representations for person re-id, which is expected universally effective for each new-coming re-id scenario.

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.

Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification

VideoObjectSearch/RandPerson 23 Jun 2020

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.

Dual Distribution Alignment Network for Generalizable Person Re-Identification

Pealing/DDAN 27 Jul 2020

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.

DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations

WangWenhao0716/DomainMix 24 Nov 2020

In this way, human annotations are no longer required, and it is scalable to large and diverse real-world datasets.

Meta Batch-Instance Normalization for Generalizable Person Re-Identification

bismex/MetaBIN CVPR 2021

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.

Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification

shengcailiao/QAConv CVPR 2022

Though online hard example mining has improved the learning efficiency to some extent, the mining in mini batches after random sampling is still limited.

TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification

ShengcaiLiao/TransMatcher NeurIPS 2021

In this work, we further investigate the possibility of applying Transformers for image matching and metric learning given pairs of images.

Benchmarks for Corruption Invariant Person Re-identification

MinghuiChen43/CIL-ReID 1 Nov 2021

When deploying person re-identification (ReID) model in safety-critical applications, it is pivotal to understanding the robustness of the model against a diverse array of image corruptions.

Calibrated Feature Decomposition for Generalizable Person Re-Identification

zkcys001/cfd 27 Nov 2021

The calibrated person representation is subtly decomposed into the identity-relevant feature, domain feature, and the remaining entangled one.