Research Article
Class-Specific Noise Injection for Improved Road Segmentation
@INPROCEEDINGS{10.1007/978-3-031-71716-1_8, author={Yukai Gu and Hao Shan and Penghui Ruan and Yutong Gao}, title={Class-Specific Noise Injection for Improved Road Segmentation}, proceedings={Machine Learning and Intelligent Communication. 8th EAI International Conference, MLICOM 2023, Beijing, China, December 17, 2023, Proceedings}, proceedings_a={MLICOM}, year={2024}, month={9}, keywords={Road segmentation Image segmentation Data augmentation Computer Vision}, doi={10.1007/978-3-031-71716-1_8} }- Yukai Gu
Hao Shan
Penghui Ruan
Yutong Gao
Year: 2024
Class-Specific Noise Injection for Improved Road Segmentation
MLICOM
Springer
DOI: 10.1007/978-3-031-71716-1_8
Abstract
In this paper, we introduce a novel class-specific noise method designed for efficient data augmentation in the realm of road segmentation. This approach is rooted in the observation that in practical image segmentation, edges area of specific class often holds higher level of importance than interiors. Distinct from traditional data augmentation techniques, our method tailors the generation of noise based on the specific class. Through experimental validation, we demonstrate that our proposed approach can significantly bolster the mean intersection over union (miou) performance of models on test datasets. Our technique holds potential for a broad spectrum of image segmentation tasks, including but not limited to medical imaging and road segmentation.
