Towards Unsupervised Online Domain Adaptation for Semantic Segmentation
Yevhen Kuznietsov, Marc Proesmans, Luc Van Gool
Abstract
In recent years, there has been significant progress in overcoming the negative effects of domain shift in semantic segmentation. Yet, existing unsupervised domain adaptation methods operate in an offline fashion, which imposes multiple restrictions on their deployment in real world scenarios. In this paper, we introduce a problem of online domain adaptation for semantic segmentation, which involves producing predictions for and, at the same time, continuously adapting a model to new frames of target domain videos. To tackle this problem, we propose a novel method which utilizes unsupervised structure-from-motion cues as the primary source of domain adaptation. By optimizing online the representation shared between depth and semantics networks, our geometry-guided algorithm achieves semantic segmentation performance comparable to state-of-the-art offline methods, without using target domain training data whatsoever.