Multi-Adversarial Domain Adaptation

TL;DR

This paper introduces a multi-adversarial domain adaptation method that uses multiple discriminators to better align complex multimode data distributions between source and target domains, improving transfer performance.

Contribution

It proposes a novel multi-adversarial framework that captures multimode structures for more precise domain alignment, surpassing existing single-discriminator approaches.

Findings

Outperforms state-of-the-art methods on standard datasets.

Effectively captures multimode structures for fine-grained alignment.

Achieves linear-time adaptation with stochastic gradient descent.

Abstract

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.