Multi-Adversarial Domain Adaptation
Published in AAAI Conference on Artificial Intelligence (AAAI) 2018, 2017
Zhongyi Pei*, Zhangjie Cao*, Mingsheng Long, Jianmin Wang. AAAI Conference on Artificial Intelligence AAAI 2018.
[Conference Version] [Arxiv] [Code]
Recent advances in deep domain adaptation reveal that adversarial learning can be embedded into deep networks to learn transferable features that reduce distribution discrepancy between the source and target domains. Existing domain adversarial adaptation methods based on single domain discriminator only align the source and target data distributions without exploiting the complex multimode structures. In this paper, we present a multi-adversarial domain adaptation (MADA) approach, which captures multimode structures to enable fine-grained alignment of different data distributions based on multiple domain discriminators. The adaptation can be achieved by stochastic gradient descent with the gradients computed by back-propagation in linear-time. Empirical evidence demonstrates that the proposed model outperforms state of the art methods on standard domain adaptation datasets.