Adapting to Continuously Shifting Domains

Andreea Bobu, Eric Tzeng, Judy Hoffman, Trevor Darrell

Abstract: Domain adaptation typically focuses on adapting a model from a single source domain to a target domain. However, in practice, this paradigm of adapting from one source to one target is limiting, as different aspects of the real world such as illumination and weather conditions vary continuously and cannot be effectively captured by two static domains. Approaches that attempt to tackle this problem by adapting from a single source to many different target domains simultaneously are consistently unable to learn across all domain shifts. Instead, we propose an adaptation method that exploits the continuity between gradually varying domains by adapting in sequence from the source to the most similar target domain. By incrementally adapting while simultaneously efficiently regularizing against prior examples, we obtain a single strong model capable of recognition within all observed domains.

Keywords: domain adaptation, unsupervised learning, computer vision, deep learning

TL;DR: We propose a flexible framework for continuous unsupervised domain adaptation that enables a single model to adapt across multiple domain shifts while maintaining consistent performance on all domains.