Domain-Symmetric Networks for Adversarial Domain Adaptation

TL;DR

This paper introduces Domain-Symmetric Networks (SymNets), a novel adversarial domain adaptation approach that enhances feature invariance at the category level, leading to improved performance on benchmark datasets.

Contribution

The paper proposes SymNets with a symmetric classifier design and a two-level domain confusion scheme for better category-level feature invariance in unsupervised domain adaptation.

Findings

Achieves state-of-the-art results on three benchmark datasets.

Demonstrates effectiveness of category-level domain confusion.

Shows improved feature invariance at finer category granularity.

Abstract

Unsupervised domain adaptation aims to learn a model of classifier for unlabeled samples on the target domain, given training data of labeled samples on the source domain. Impressive progress is made recently by learning invariant features via domain-adversarial training of deep networks. In spite of the recent progress, domain adaptation is still limited in achieving the invariance of feature distributions at a finer category level. To this end, we propose in this paper a new domain adaptation method called Domain-Symmetric Networks (SymNets). The proposed SymNet is based on a symmetric design of source and target task classifiers, based on which we also construct an additional classifier that shares with them its layer neurons. To train the SymNet, we propose a novel adversarial learning objective whose key design is based on a two-level domain confusion scheme, where the category-level confusion loss improves over the domain-level one by driving the learning of intermediate network features to be invariant at the corresponding categories of the two domains. Both domain discrimination and domain confusion are implemented based on the constructed additional classifier. Since target samples are unlabeled, we also propose a scheme of cross-domain training to help learn the target classifier. Careful ablation studies show the efficacy of our proposed method. In particular, based on commonly used base networks, our SymNets achieve the new state of the art on three benchmark domain adaptation datasets.