Multi-Adversarial Domain Adaptation
This work addresses domain adaptation for machine learning by improving alignment of data distributions, but it appears incremental as it builds on existing adversarial methods.
The paper tackles the problem of aligning complex multimode structures in domain adaptation by proposing a multi-adversarial approach, which outperforms state-of-the-art methods on standard datasets.
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.