Journal
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
Volume -, Issue -, Pages 2829-2839Publisher
IEEE COMPUTER SOC
DOI: 10.1109/CVPRW53098.2021.00318
Keywords
-
Categories
Funding
- Italian Ministry for Education (MIUR) [232/2016]
- SID project Semantic Segmentation in the Wild
Ask authors/readers for more resources
This paper introduces feature-level space-shaping regularization strategies to reduce domain discrepancy in semantic segmentation, achieving state-of-the-art results in the autonomous driving setting. By enforcing clustering objectives, perpendicularity constraints, and norm alignment goals on feature vectors corresponding to source and target samples, along with proposing a novel measure to capture the relative efficacy of adaptation strategies compared to supervised training, the effectiveness of such methods has been verified in multiple synthetic-to-real road scenes benchmarks.
Deep convolutional neural networks for semantic segmentation achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the training data; second, they require a huge amount of labeled data for their optimization. In this paper, we introduce feature-level space-shaping regularization strategies to reduce the domain discrepancy in semantic segmentation. In particular, for this purpose we jointly enforce a clustering objective, a perpendicularity constraint and a norm alignment goal on the feature vectors corresponding to source and target samples. Additionally, we propose a novel measure able to capture the relative efficacy of an adaptation strategy compared to supervised training. We verify the effectiveness of such methods in the autonomous driving setting achieving state-of-the-art results in multiple synthetic-to-real road scenes benchmarks.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available