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.
翻译:(DG) 个人重新定位(ReID) 的目的是在培训时间测试各种看不见领域,而没有访问目标域数据,这是一个现实但具有挑战性的问题。与对不同领域采用相同模式的方法相比,专家混合(MOE)利用多个特定域网络来利用不同领域之间的互补信息,取得了令人印象深刻的结果。然而,以前以教育部为基础的DG ReID方法的模型规模很大,来源域数增加,其中多数忽视了对1994年域内变异特性的利用。为了处理上述两个问题,本文件为DG 个人再识别(META)提出了一个名为“通过成形聚合(META)嵌入目标域数据(META)”的新方法。为避免大型模型规模,META的专家并不采用每个来源域间的分支网络,而是分享所有参数,但批次正常化层除外。除了多位专家外,META 利用度常态正常化(IN) 并将其引入一个全球分支,以追求1994年域内变异特性。同时,META专家通过正统域域域域域域域域域域域域域域域(MA) 目标样样样和大源域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域域规则化(IMA) 将一个预期的变变码(MA) 的变变变变变码) 的变变码化(MI) 的变变码) 内变码校码化(IM) 的变变码化分析模型化模型成的变变变码化(MIS变码化) 的变码化模型的变变码化模型的变码化模型的变码化模型(MA) 内的变码化) 变变码化) 变码化模型(MA) 变变变码化模型(MA(MA) 变码化模型化) 变码化) 变码化模型的变码化模型化模型化模型化模型化模型变码化变变变码化) 变码分析模型(MA) 变码化) 变码化) 变码变码化变码化变码化变码化变码(MIS变码化) 的