Transfer Learning with Dynamic Adversarial Adaptation Network

TL;DR

This paper introduces DAAN, a novel deep transfer learning method that dynamically balances global and local domain distribution alignment using adversarial learning, improving classification accuracy.

Contribution

DAAN is the first method to perform dynamic adversarial distribution adaptation, quantitatively evaluating and balancing global and local domain contributions.

Findings

DAAN outperforms state-of-the-art methods in classification accuracy.

It effectively balances global and local distribution alignment.

The approach is easy to implement and train in real applications.

Abstract

The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain adaptation methods either learn a single domain discriminator to align the global source and target distributions or pay attention to align subdomains based on multiple discriminators. However, in real applications, the marginal (global) and conditional (local) distributions between domains are often contributing differently to the adaptation. There is currently no method to dynamically and quantitatively evaluate the relative importance of these two distributions for adversarial learning. In this paper, we propose a novel Dynamic Adversarial Adaptation Network (DAAN) to dynamically learn domain-invariant representations while quantitatively evaluate the relative importance of global and local domain distributions. To the best of our knowledge, DAAN is the first attempt to perform dynamic adversarial distribution adaptation for deep adversarial learning. DAAN is extremely easy to implement and train in real applications. We theoretically analyze the effectiveness of DAAN, and it can also be explained in an attention strategy. Extensive experiments demonstrate that DAAN achieves better classification accuracy compared to state-of-the-art deep and adversarial methods. Results also imply the necessity and effectiveness of the dynamic distribution adaptation in adversarial transfer learning.