English

Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification

Computer Vision and Pattern Recognition 2022-07-22 v3 Artificial Intelligence

Abstract

Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time, which is a realistic but challenging problem. In contrast to methods assuming an identical model for different domains, Mixture of Experts (MoE) exploits multiple domain-specific networks for leveraging complementary information between domains, obtaining impressive results. However, prior MoE-based DG ReID methods suffer from a large model size with the increase of the number of source domains, and most of them overlook the exploitation of domain-invariant characteristics. To handle the two issues above, this paper presents a new approach called Mimic Embedding via adapTive Aggregation (META) for DG person ReID. To avoid the large model size, experts in META do not adopt a branch network for each source domain but share all the parameters except for the batch normalization layers. Besides multiple experts, META leverages Instance Normalization (IN) and introduces it into a global branch to pursue invariant features across domains. Meanwhile, META considers the relevance of an unseen target sample and source domains via normalization statistics and develops an aggregation module to adaptively integrate multiple experts for mimicking unseen target domain. Benefiting from a proposed consistency loss and an episodic training algorithm, META is expected to mimic embedding for a truly unseen target domain. Extensive experiments verify that META surpasses state-of-the-art DG person ReID methods by a large margin. Our code is available at https://github.com/xbq1994/META.

Keywords

Cite

@article{arxiv.2112.08684,
  title  = {Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification},
  author = {Boqiang Xu and Jian Liang and Lingxiao He and Zhenan Sun},
  journal= {arXiv preprint arXiv:2112.08684},
  year   = {2022}
}

Comments

ECCV 2022

R2 v1 2026-06-24T08:19:53.000Z