Domain-invariant Prototypes for Semantic Segmentation
This addresses the need for efficient domain adaptation in semantic segmentation, reducing reliance on annotated data and complex training procedures, though it is incremental as it builds on existing self-training and few-shot learning ideas.
The paper tackles the problem of domain adaptive semantic segmentation by proposing a unified framework that learns domain-invariant prototypes, enabling one-stage training without large-scale unannotated target data. It achieves competitive performance on benchmarks like GTA5-to-Cityscapes and SYNTHIA-to-Cityscapes.
Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have been devoted to domain adaptive semantic segmentation that focuses on transferring semantic knowledge from a labeled source domain to an unlabeled target domain. Existing self-training methods typically require multiple rounds of training, while another popular framework based on adversarial training is known to be sensitive to hyper-parameters. In this paper, we present an easy-to-train framework that learns domain-invariant prototypes for domain adaptive semantic segmentation. In particular, we show that domain adaptation shares a common character with few-shot learning in that both aim to recognize some types of unseen data with knowledge learned from large amounts of seen data. Thus, we propose a unified framework for domain adaptation and few-shot learning. The core idea is to use the class prototypes extracted from few-shot annotated target images to classify pixels of both source images and target images. Our method involves only one-stage training and does not need to be trained on large-scale un-annotated target images. Moreover, our method can be extended to variants of both domain adaptation and few-shot learning. Experiments on adapting GTA5-to-Cityscapes and SYNTHIA-to-Cityscapes show that our method achieves competitive performance to state-of-the-art.