PT Journal
AU Jose Luis Gomez
   Gabriel Villalonga
   Antonio Lopez
TI Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models
SO Sensors – Special Issue on “Machine Learning for Autonomous Driving Perception and Prediction”
JI SENS
PY 2023
BP 621
VL 23
IS 2
DE Domain adaptation; semi-supervised learning; Semantic segmentation; Autonomous driving
AB 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.
ER