Target-Style-Aware Unsupervised Domain Adaptation for Object Detection

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 215
  • Download : 0
Vision modules running on mobility platforms, such as robots and cars, often face challenging situations such as a domain shift where the distributions of training (source) data and test (target) data are different. The domain shift is caused by several variation factors, such as style, camera viewpoint, object appearance, object size, backgrounds, and scene layout. In this work, we propose an object detection training framework for unsupervised domain-style adaptation. The proposed training framework transfers target-style information to source samples and simultaneously trains the detection network with these target-stylized source samples in an end-to-end manner. The detection network can learn the target domain from the target-stylized source samples. The style is extracted from object areas obtained by using pseudo-labels to reflect the style of the object areas more than that of the irrelevant backgrounds. We empirically verified that the proposed methods improve detection accuracy in diverse domain shift scenarios using the Cityscapes, FoggyCityscapes, Sim10k, BDD100k, PASCAL, and Watercolor datasets.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2021-04
Language
English
Article Type
Article
Citation

IEEE ROBOTICS AND AUTOMATION LETTERS, v.6, no.2, pp.3825 - 3832

ISSN
2377-3766
DOI
10.1109/LRA.2021.3062333
URI
http://hdl.handle.net/10203/283661
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0