Co-Training for On-Board Deep Object Detection
Villalonga, Gabriel (Centre de Visió per Computador (Bellaterra, Catalunya))
López Peña, Antonio M. (Universitat Autònoma de Barcelona. Departament de Ciències de la Computació)

Fecha:	2020
Resumen:	Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models. This was the case when visual tasks relied on handcrafted features and shallow machine learning and, despite its unprecedented performance gains, the problem remains open within the deep learning paradigm due to its data-hungry nature. Best performing deep vision-based object detectors are trained in a supervised manner by relying on human-labeled bounding boxes which localize class instances (i. e. objects) within the training images. Thus, object detection is one of such tasks for which human labeling is a major bottleneck. In this article, we assess co-training as a semi-supervised learning method for self-labeling objects in unlabeled images, so reducing the human-labeling effort for developing deep object detectors. Our study pays special attention to a scenario involving domain shift; in particular, when we have automatically generated virtual-world images with object bounding boxes and we have real-world images which are unlabeled. Moreover, we are particularly interested in using co-training for deep object detection in the context of driver assistance systems and/or self-driving vehicles. Thus, using well-established datasets and protocols for object detection in these application contexts, we will show how co-training is a paradigm worth to pursue for alleviating object labeling, working both alone and together with task-agnostic domain adaptation.
Ayudas:	Agencia Estatal de Investigación TIN2017-88709-R
Derechos:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Lengua:	Anglès
Documento:	Article ; recerca ; Versió publicada
Materia:	Object detection ; Labeling ; Task analysis ; Detectors ; Data models ; Predictive models ; Computer vision ; Co-training ; Domain adaptation ; Vision-based object detection ; ADAS ; Self-driving
Publicado en:	IEEE Access, Vol. 8 (October 2020) p. 194441-194456, ISSN 2169-3536

DOI: 10.1109/ACCESS.2020.3032024

16 p, 5.6 MB

El registro aparece en las colecciones:
Artículos > Artículos de investigación
Artículos > Artículos publicados