Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Automation and Machine Learning
  4. Vol 4, Issue 1, 2023

Two-step Domain Adaptive Semantic Segmentation Algorithm of Driving Scene

Download as PDF

DOI: 10.23977/autml.2023.040105 | Downloads: 18 | Views: 326

Author(s)

Zhou Su 1,2, Yuan Tanghu 1, Yi Yuqian 2

Affiliation(s)

1 School of Automotive Studies, Tongji University, Shanghai, China
2 Sino-German College, Tongji University, Shanghai, China

Corresponding Author

Yuan Tanghu

ABSTRACT

Semantic segmentation of driving scenes is an important task in the field of automatic driving perception. The existing semantic segmentation based on deep learning method needs a lot of manpower cost to label data, and the changeable driving scenes will also lead to the performance degradation of semantic segmentation model in practical application. Therefore, in this paper, labeled computer-generated images are used as source domain data, unlabeled real driving scene images are used as target domain data, and unsupervised domain adaptive method is used to transfer knowledge when the target domain data is unlabeled. Based on the one-step domain adaptive semantic segmentation algorithm, a two-step domain adaptive semantic segmentation algorithm is proposed, and an image quality evaluation module is introduced to optimize the algorithm, so as to improve the performance index of cross-domain semantic segmentation tasks to some extent and reduce the dependence on data labeling and labeling cost.

KEYWORDS

Automated driving, Computer vision, Semantic segmentation, Antagonistic

CITE THIS PAPER

Zhou Su, Yuan Tanghu, Yi Yuqian, Two-step Domain Adaptive Semantic Segmentation Algorithm of Driving Scene. Automation and Machine Learning (2023) Vol. 4: 32-40. DOI: http://dx.doi.org/10.23977/autml.2023.040105.

REFERENCES

[1] Klare B F, Klein B, Taborsky E, et al. Pushing the Frontiers of Unconstrained Face Detection and Recognition: IARPA Janus Benchmark A[C]// IEEE Computer Vision and Pattern Recognition (CVPR), 2015.
[2] Deng W, Liang Z, Kang G, et al. Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification [J]. 2017.
[3] Wei L, Zhang S, Wen G, et al. Person Transfer GAN to Bridge Domain Gap for Person Re-Identification[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.
[4] Zhong Z, Liang Z, Zheng Z, et al. Camera Style Adaptation for Person Re-identification[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.
[5] Chen Y, Li W, Sakaridis C, et al. Domain Adaptive Faster R-CNN for Object Detection in the Wild[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.
[6] Inoue N, Furuta R, Yamasaki T, et al. Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.
[7] Kim T, Jeong M, Kim S, et al. Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[8] Roychowdhury A, Chakrabarty P, Singh A, et al. Automatic Adaptation of Object Detectors to New Domains Using Self-Training[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[9] Vincent O. Rebecca, and Olusegun Folorunso. "A descriptive algorithm for sobel image edge detection." Proceedings of informing science & IT education conference (InSITE). Vol. 40. 2009.
[10] Wang X, Cai Z, Gao D, et al. Towards Universal Object Detection by Domain Attention [J]. IEEE, 2019.
[11] Zhu X, Pang J, Yang C, et al. Adapting Object Detectors via Selective Cross-Domain Alignment[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[12] Wang T, Zhang X, Yuan L, et al. Few-shot Adaptive Faster R-CNN[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019. 
[13] Pan F, Shin I, Rameau F, et al. Unsupervised Intra-Domain Adaptation for Semantic Segmentation through Self-Supervision [J]. Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 990
Visits: 48955

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.