Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
10-2021
Abstract
In this paper, we seek reasons for the two major failure cases in Semantic Segmentation (SS): 1) missing small objects or minor object parts, and 2) mislabeling minor parts of large objects as wrong classes. We have an interesting finding that Failure-1 is due to the underuse of detailed features and Failure-2 is due to the underuse of visual contexts. To help the model learn a better trade-off, we introduce several Self-Regulation (SR) losses for training SS neural networks. By “self”, we mean that the losses are from the model per se without using any additional data or supervision. By applying the SR losses, the deep layer features are regulated by the shallow ones to preserve more details; meanwhile, shallow layer classification logits are regulated by the deep ones to capture more semantics. We conduct extensive experiments on both weakly and fully supervised SS tasks, and the results show that our approach consistently surpasses the baselines. We also validate that SR losses are easy to implement in various state-of-the-art SS models, e.g., SPGNet [7] and OCRNet [62], incurring little computational overhead during training and none for testing.
Discipline
Graphics and Human Computer Interfaces
Research Areas
Intelligent Systems and Optimization
Publication
Proceedings of 2021 International Conference on Computer Vision, Virtual Conference, October 11-17
First Page
6953
Last Page
6963
City or Country
Virtual Conference
Citation
ZHANG, Dong; ZHANG, Hanwang; TANG, Jinhui; HUA, Xian-Sheng; and SUN, Qianru.
Self-regulation for semantic segmentation. (2021). Proceedings of 2021 International Conference on Computer Vision, Virtual Conference, October 11-17. 6953-6963.
Available at: https://ink.library.smu.edu.sg/sis_research/6230
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.