Unsupervised Domain Adaptation by Optical Flow Augmentation in Semantic Segmentation
This addresses the costly labeling issue for real-life images in semantic segmentation, but appears incremental as it builds on existing techniques like class balanced self-training and flow map augmentation.
The paper tackles the problem of domain adaptation in semantic segmentation by augmenting images with dense optical flow maps to reduce the domain gap between simulated and real-life images, aiming to eliminate the need for labeling real-life datasets.
It is expensive to generate real-life image labels and there is a domain gap between real-life and simulated images, hence a model trained on the latter cannot adapt to the former. Solving this can totally eliminate the need for labeling real-life datasets completely. Class balanced self-training is one of the existing techniques that attempt to reduce the domain gap. Moreover, augmenting RGB with flow maps has improved performance in simple semantic segmentation and geometry is preserved across domains. Hence, by augmenting images with dense optical flow map, domain adaptation in semantic segmentation can be improved.