Unsupervised Domain Adaptation by Optical Flow Augmentation in Semantic Segmentation [article]

Oluwafemi Azeez
2019 arXiv   pre-print
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
more » ... domains. Hence, by augmenting images with dense optical flow map, domain adaptation in semantic segmentation can be improved.
arXiv:1911.09652v1 fatcat:qq5shbwxpvd2neetnvx45x2qmi