Generalizable Person Re-identification with Relevance-aware Mixture of Experts

05/19/2021
by   Yongxing Dai, et al.
7

Domain generalizable (DG) person re-identification (ReID) is a challenging problem because we cannot access any unseen target domain data during training. Almost all the existing DG ReID methods follow the same pipeline where they use a hybrid dataset from multiple source domains for training, and then directly apply the trained model to the unseen target domains for testing. These methods often neglect individual source domains' discriminative characteristics and their relevances w.r.t. the unseen target domains, though both of which can be leveraged to help the model's generalization. To handle the above two issues, we propose a novel method called the relevance-aware mixture of experts (RaMoE), using an effective voting-based mixture mechanism to dynamically leverage source domains' diverse characteristics to improve the model's generalization. Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics. Besides, we design a voting network to adaptively integrate all the experts' features into the more generalizable aggregated features with domain relevance. Considering the target domains' invisibility during training, we propose a novel learning-to-learn algorithm combined with our relation alignment loss to update the voting network. Extensive experiments demonstrate that our proposed RaMoE outperforms the state-of-the-art methods.

READ FULL TEXT
research
12/16/2021

META: Mimicking Embedding via oThers' Aggregation for Generalizable Person Re-identification

Domain generalizable (DG) person re-identification (ReID) aims to test a...
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
06/08/2022

Sparse Fusion Mixture-of-Experts are Domain Generalizable Learners

Domain generalization (DG) aims at learning generalizable models under d...
research
11/29/2021

TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification

Domain generalizable person re-identification aims to apply a trained mo...
research
06/29/2021

Domain-Class Correlation Decomposition for Generalizable Person Re-Identification

Domain generalization in person re-identification is a highly important ...
research
08/15/2022

CAME: Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation

The scene graph generation has gained tremendous progress in recent year...
research
03/05/2022

Federated and Generalized Person Re-identification through Domain and Feature Hallucinating

In this paper, we study the problem of federated domain generalization (...

Please sign up or login with your details

Forgot password? Click here to reset