DEX: Domain Embedding Expansion for Generalized Person Re-identification

10/21/2021
by   Eugene P. W. Ang, et al.
0

In recent years, supervised Person Re-identification (Person ReID) approaches have demonstrated excellent performance. However, when these methods are applied to inputs from a different camera network, they typically suffer from significant performance degradation. Different from most domain adaptation (DA) approaches addressing this issue, we focus on developing a domain generalization (DG) Person ReID model that can be deployed without additional fine-tuning or adaptation. In this paper, we propose the Domain Embedding Expansion (DEX) module. DEX dynamically manipulates and augments deep features based on person and domain labels during training, significantly improving the generalization capability and robustness of Person ReID models to unseen domains. We also developed a light version of DEX (DEXLite), applying negative sampling techniques to scale to larger datasets and reduce memory usage for multi-branch networks. Our proposed DEX and DEXLite can be combined with many existing methods, Bag-of-Tricks (BagTricks), the Multi-Granularity Network (MGN), and Part-Based Convolutional Baseline (PCB), in a plug-and-play manner. With DEX and DEXLite, existing methods can gain significant improvements when tested on other unseen datasets, thereby demonstrating the general applicability of our method. Our solution outperforms the state-of-the-art DG Person ReID methods in all large-scale benchmarks as well as in most the small-scale benchmarks.

READ FULL TEXT
research
11/25/2020

Multi-Domain Adversarial Feature Generalization for Person Re-Identification

With the assistance of sophisticated training methods applied to single ...
research
05/26/2021

Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification

Recent years have witnessed significant progress in person re-identifica...
research
03/17/2019

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

This paper explores a simple and efficient baseline for person re-identi...
research
04/26/2018

Domain Adaptation through Synthesis for Unsupervised Person Re-identification

Drastic variations in illumination across surveillance cameras make the ...
research
10/15/2019

Attention Network Robustification for Person ReID

The task of person re-identification (ReID) has attracted growing attent...
research
07/04/2019

A Survey of Pruning Methods for Efficient Person Re-identification Across Domains

Recent years have witnessed a substantial increase in the deep learning ...
research
05/16/2018

An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification

In recent years, a variety of proposed methods based on deep convolution...

Please sign up or login with your details

Forgot password? Click here to reset