IEEE - Institute of Electrical and Electronics Engineers, Inc. - Multi-Task Self-Supervised Visual Representation Learning for Monocular Road Segmentation

2018 IEEE International Conference on Multimedia and Expo (ICME)

Author(s): Jaehoon Cho ; Youngjung Kim ; Hyungjoo Jung ; Changjae Oh ; Jaesung Youn ; Kwanghoon Sohn
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 July 2018
Conference Location: San Diego, CA, USA, USA
Conference Date: 23 July 2018
Page(s): 1 - 6
ISBN (Electronic): 978-1-5386-1737-3
ISBN (USB): 978-1-5386-1736-6
ISSN (Electronic): 1945-788X
DOI: 10.1109/ICME.2018.8486472
Regular:

Training deep networks commonly follows the supervised learning paradigm, which requires large-scale semantically-labeled data. The construction of such dataset is one of the major... View More

Advertisement