Unsupervised Domain Expansion for Visual Categorization

TL;DR

This paper introduces unsupervised domain expansion (UDE), a new task that adapts models to a target domain while maintaining performance on the source, using a knowledge distillation approach called KDDE.

Contribution

It proposes the UDE task and the KDDE method, which can adapt existing models to new domains without sacrificing source domain performance.

Findings

KDDE outperforms four baselines on Office-Home and DomainNet.

UDE balances performance on source and target domains.

Current UDA models often reduce source domain performance when adapting.

Abstract

Expanding visual categorization into a novel domain without the need of extra annotation has been a long-term interest for multimedia intelligence. Previously, this challenge has been approached by unsupervised domain adaptation (UDA). Given labeled data from a source domain and unlabeled data from a target domain, UDA seeks for a deep representation that is both discriminative and domain-invariant. While UDA focuses on the target domain, we argue that the performance on both source and target domains matters, as in practice which domain a test example comes from is unknown. In this paper we extend UDA by proposing a new task called unsupervised domain expansion (UDE), which aims to adapt a deep model for the target domain with its unlabeled data, meanwhile maintaining the model's performance on the source domain. We propose Knowledge Distillation Domain Expansion (KDDE) as a general method for the UDE task. Its domain-adaptation module can be instantiated with any existing model. We develop a knowledge distillation based learning mechanism, enabling KDDE to optimize a single objective wherein the source and target domains are equally treated. Extensive experiments on two major benchmarks, i.e., Office-Home and DomainNet, show that KDDE compares favorably against four competitive baselines, i.e., DDC, DANN, DAAN, and CDAN, for both UDA and UDE tasks. Our study also reveals that the current UDA models improve their performance on the target domain at the cost of noticeable performance loss on the source domain.