Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
10-2022
Abstract
State-of-the-art (SOTA) anomaly segmentation approaches on complex urban driving scenes explore pixel-wise classification uncertainty learned from outlier exposure, or external reconstruction models. However, previous uncertainty approaches that directly associate high uncertainty to anomaly may sometimes lead to incorrect anomaly predictions, and external reconstruction models tend to be too inefficient for real-time self-driving embedded systems. In this paper, we propose a new anomaly segmentation method, named pixel-wise energy-biased abstention learning (PEBAL), that explores pixel-wise abstention learning (AL) with a model that learns an adaptive pixel-level anomaly class, and an energy-based model (EBM) that learns inlier pixel distribution. More specifically, PEBAL is based on a non-trivial joint training of EBM and AL, where EBM is trained to output high-energy for anomaly pixels (from outlier exposure) and AL is trained such that these high-energy pixels receive adaptive low penalty for being included to the anomaly class. We extensively evaluate PEBAL against the SOTA and show that it achieves the best performance across four benchmarks. Code is available at https://github.com/tianyu0207/PEBAL.
Discipline
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces
Research Areas
Intelligent Systems and Optimization
Publication
Computer Vision ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27: Proceedings
Volume
13699
First Page
246
Last Page
263
ISBN
9783031198427
Identifier
10.1007/978-3-031-19842-7_15
Publisher
Springer
City or Country
Cham
Citation
TIAN, Yu; LIU, Yuyuan; PANG, Guansong; LIU, Fengbei; CHEN, Yuanhong; and CARNEIRO, Gustavo.
Pixel-wise energy-biased abstention learning for anomaly segmentation on complex urban driving scenes. (2022). Computer Vision ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27: Proceedings. 13699, 246-263.
Available at: https://ink.library.smu.edu.sg/sis_research/7058
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1007/978-3-031-19842-7_15
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons