Striking a Balance in Unsupervised Fine-Grained Domain Adaptation Using Adversarial Learning

摘要

Fine-grained domain adaptation is an emerging yet very challenging task in representation learning. In this paper, we analyze a possible reason for the poor performance in fine-grained domain adaptation, which is the difficulty in striking a balance between distribution alignment and fine-grained variations elimination. Furthermore, we propose an adversarial fine-grained domain adaptation framework as a step towards alleviating the underlying conflict between fine-grained variations elimination and domain adaptation. Specifically, our adversarial framework consists of two key modules: a joint label predictor for conditional distribution alignment and a rectifier for fine-grained variations elimination. The key balance can be achieved through the adversarial learning. Besides, experiments on domain adaptation benchmark and fine-grained dataset validate the effectiveness of our framework and show that our framework consistently outperforms the state-of-the-art methods including RTN, MADA, Multi-Task, and DASA.