We consider multi-source free domain adaptation, the problem of adapting multiple existing models to a new domain without accessing the source data. Among existing approaches, methods based on model ensemble are effective in both the source and target domains, but incur significantly increased computational costs. Towards this dilemma, in this work, we propose a novel framework called SepRep-Net, which tackles multi-source free domain adaptation via model Separation and Reparameterization.Concretely, SepRep-Net reassembled multiple existing models to a unified network, while maintaining separate pathways (Separation). During training, separate pathways are optimized in parallel with the information exchange regularly performed via an additional feature merging unit. With our specific design, these pathways can be further reparameterized into a single one to facilitate inference (Reparameterization). SepRep-Net is characterized by 1) effectiveness: competitive performance on the target domain, 2) efficiency: low computational costs, and 3) generalizability: maintaining more source knowledge than existing solutions. As a general approach, SepRep-Net can be seamlessly plugged into various methods. Extensive experiments validate the performance of SepRep-Net on mainstream benchmarks.

翻译：我们研究了多源无源域适应问题，即在无法访问源数据的情况下，将多个现有模型适应到新域的过程。在现有方法中，基于模型集成的方法在源域和目标域均表现出色，但显著增加了计算成本。针对这一困境，本文提出了一种名为SepRep-Net的新型框架，通过模型分离与重参数化来解决多源无源域适应问题。具体而言，SepRep-Net将多个现有模型重组为统一网络，同时保持独立路径（分离）。训练阶段，独立路径通过额外特征融合模块定期进行信息交换，并行优化。基于我们的特殊设计，这些路径可进一步重参数化为单一路径以加速推理（重参数化）。SepRep-Net具有三大特性：1）有效性：在目标域上性能优异；2）高效性：计算成本低；3）泛化性：比现有方案保留更多源知识。作为通用方法，SepRep-Net可无缝集成到各类方法中。大量实验验证了SepRep-Net在主流基准测试上的性能表现。