%0 Journal Article
%T Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models
%A Jose Luis Gomez
%A Gabriel Villalonga
%A Antonio Lopez
%J Sensors – Special Issue on “Machine Learning for Autonomous Driving Perception and Prediction”
%D 2023
%V 23
%N 2
%F Jose Luis Gomez2023
%O ADAS; no proj
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3705), last updated on Wed, 31 May 2023 15:42:34 +0200
%X Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated labels together with unlabeled real-world images is a promising alternative. This implies to address an unsupervised domain adaptation (UDA) problem. In this paper, we propose a new co-training procedure for synth-to-real UDA of semanticsegmentation models. It consists of a self-training stage, which provides two domain-adapted models, and a model collaboration loop for the mutual improvement of these two models. These models are then used to provide the final semantic segmentation labels (pseudo-labels) for the real-world images. The overallprocedure treats the deep models as black boxes and drives their collaboration at the level of pseudo-labeled target images, i.e., neither modifying loss functions is required, nor explicit feature alignment. We test our proposal on standard synthetic and real-world datasets for on-board semantic segmentation. Ourprocedure shows improvements ranging from ∼13 to ∼26 mIoU points over baselines, so establishing new state-of-the-art results.
%K Domain adaptation
%K semi-supervised learning
%K Semantic segmentation
%K Autonomous driving
%U https://www.mdpi.com/1424-8220/23/2/621
%P 621