Deep Cocktail Network: Multi-Source Unsupervised Domain Adaptation With Category Shift

Ruijia Xu, Ziliang Chen, Wangmeng Zuo, Junjie Yan, Liang Lin

Abstract: Most existing unsupervised domain adaptation (UDA) methods are based upon the assumption that source labeled data come from an identical underlying distribution. Whereas in practical scenario, labeled instances are typically collected from diverse sources. Moreover, those sources may not completely share their categories, which further brings a category shift challenge to multi-source (unsupervised) domain adaptation (MDA). In this paper, we propose a deep cocktail network (DCTN), to battle the domain and category shifts among multiple sources. Motivated by the theoretical results in cite{mansour2009domain}, the target distribution can be represented as the weighted combination of source distributions, and, the training of MDA via DCTN is then performed as two alternating steps: i) It deploys multi-way adversarial learning to minimize the discrepancy between the target and each of the multiple source domains, which also obtains the source-specific perplexity scores to denote the possibilities that a target sample belongs to different source domains. ii) The multi-source category classifiers are integrated with the perplexity scores to classify target sample, and the pseudo-labeled target samples together with source samples are utilized to update the multi-source category classifier and the representation module. We evaluate DCTN in three domain adaptation benchmarks, which clearly demonstrate the superiority of our framework.