Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification
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.
Code (1)
Tasks
Generalizable Person Re-identificationMixture-of-ExpertsPerson Re-IdentificationUnsupervised Domain AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Model Generalization on Text Attribute Graphs: Principles with Large Language Models
Large language models (LLMs) have recently been introduced to graph learning, aiming to extend their zero-shot generalization success to tasks where labeled graph data is scarce. Among these applications, inference over …
AttributeGraph LearningTAGZero-shot GeneralizationFedPrism: Adaptive Personalized Federated Learning under Non-IID Data
Federated Learning (FL) suffers significant performance degradation in real-world deployments characterized by moderate to extreme statistical heterogeneity (non-IID client data). While global aggregation strategies prom…
Personalized Federated LearningFar From Sight, Far From Mind: Inverse Distance Weighting for Graph Federated Recommendation
Graph federated recommendation systems offer a privacy-preserving alternative to traditional centralized recommendation architectures, which often raise concerns about data security. While federated learning enables pers…
Recommendation SystemsFederated LearningAdaptive Cross-Domain Learning for Generalizable Person Re-Identification
Domain Generalizable Person Re-Identification (DG-ReID) is a more practical ReID task that is trained from multiple source domains and tested on the unseen target domains. Most existing methods are challenged for dealing…
Generalizable Person Re-identificationPerson Re-IdentificationUnsupervised Domain AdaptationThe Adaptation Paradox: Agency vs. Mimicry in Companion Chatbots
Generative AI powers a growing wave of companion chatbots, yet principles for fostering genuine connection remain unsettled. We test two routes: visible user authorship versus covert language-style mimicry. In a preregis…