Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
This addresses the problem of unsupervised domain adaptation for person re-identification, which is incremental as it explores ensemble learning in this specific context.
The paper tackles domain adaptive person re-identification by proposing a multiple expert brainstorming network (MEB-Net) that uses mutual learning among pre-trained expert models with different architectures, achieving superior performance on large-scale datasets like Market-1501 and DukeMTMC-reID.
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.