Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
复制标题
DOI：
10.1007/978-3-030-58571-6_35
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Yunpeng Zhai;Qixiang Ye;Shijian Lu;Mengxi Jia;Rongrong Ji;Yonghong Tian
中科院分区：
文献类型：
--
作者：
Yunpeng Zhai;Qixiang Ye;Shijian Lu;Mengxi Jia;Rongrong Ji;Yonghong Tian
Often the best performing deep neural models are ensembles of multiple base-level networks, nevertheless, ensemble learning with respect to domain adaptive person re-ID remains unexplored. In this paper, we propose a multiple expert brainstorming network (MEB-Net) for domain adaptive person re-ID, opening up a promising direction about model ensemble problem under unsupervised conditions. MEB-Net adopts a mutual learning strategy, where multiple networks with different architectures are pre-trained within a source domain as expert models equipped with specific features and knowledge, while the adaptation is then accomplished through brainstorming (mutual learning) among expert models. MEB-Net accommodates the heterogeneity of experts learned with different architectures and enhances discrimination capability of the adapted re-ID model, by introducing a regularization scheme about authority of experts. Extensive experiments on large-scale datasets (Market-1501 and DukeMTMC-reID) demonstrate the superior performance of MEB-Net over the state-of-the-arts. Code is available at https://github.com/YunpengZhai/MEB-Net .
