Predictive uncertainties for multi-task learning network

Tianxiao Gao; Wu Wei; Xinmei Wang; Qiuda Yu; Zhun Fan

doi:10.1117/12.2637183

15 June 2022 Predictive uncertainties for multi-task learning network

Tianxiao Gao, Wu Wei, Xinmei Wang, Qiuda Yu, Zhun Fan

Author Affiliations +

Proceedings Volume 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022); 122851B (2022) https://doi.org/10.1117/12.2637183
Event: International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 2022, Zhuhai, China

Abstract

Depth estimation and semantic segmentation are important for applications such as autonomous driving cars and minimally invasive surgery. However, the imperfect predictions make even networks with best performance difficult to apply to these high-safety-demand domains. Therefore, in this paper, using the variational representation method, we propose two uncertainty losses to enable multi-task learning network to predict the uncertainties respectively for predictions of depth values and semantic labels. The experimental results on NYU-Depth-v2 and SUN-RGBD datasets demonstrate the novelty and effectiveness of our proposed uncertainty losses.

Citation Download Citation

Tianxiao Gao, Wu Wei, Xinmei Wang, Qiuda Yu, and Zhun Fan "Predictive uncertainties for multi-task learning network", Proc. SPIE 12285, International Conference on Advanced Algorithms and Neural Networks (AANN 2022), 122851B (15 June 2022); https://doi.org/10.1117/12.2637183

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE