Co-training for unsupervised domain adaptation of semantic segmentation models
Gomez Zurita, Jose Luis (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)
Villalonga, Gabriel (Centre de Visió per Computador (Bellaterra, Catalunya))
López Peña, Antonio M. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)

Data:	2023
Resum:	Semantic image segmentation is a core task for autonomous driving, which is performed by deep models. Since training these models draws to a curse of human-based image labeling, the use of synthetic images with automatically generated labels together with unlabeled real-world images is a promising alternative. This implies addressing an unsupervised domain adaptation (UDA) problem. In this paper, we propose a new co-training procedure for synth-to-real UDA of semantic segmentation models. It performs iterations where the (unlabeled) real-world training images are labeled by intermediate deep models trained with both the (labeled) synthetic images and the real-world ones labeled in previous iterations. More specifically, a self-training stage provides two domain-adapted models and a model collaboration loop allows the mutual improvement of these two models. The final semantic segmentation labels (pseudo-labels) for the real-world images are provided by these two models. The overall procedure 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 onboard semantic segmentation. Our procedure shows improvements ranging from approximately 13 to 31 mIoU points over baselines.
Ajuts:	Agencia Estatal de Investigación PID2020-115734RB-C21 Ministerio de Educación, Cultura y Deporte FPU16/04131
Nota:	Altres ajuts: Antonio M. López acknowledges the financial support to his general research activities given by ICREA under the ICREA Academia Program
Drets:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Llengua:	Anglès
Document:	Article ; recerca ; Versió publicada
Matèria:	Domain adaptation ; Semi-supervised learning ; Semantic segmentation ; Autonomous driving
Publicat a:	Sensors (Basel, Switzerland), Vol. 23, issue 2 (Jan. 2023) , art. 621, ISSN 1424-8220

DOI: 10.3390/s23020621
PMID: 36679419

28 p, 13.4 MB

El registre apareix a les col·leccions:
Articles > Articles de recerca
Articles > Articles publicats