Please use this identifier to cite or link to this item:
Title: Weakly-supervised cross-domain road scene segmentation via multi-level curriculum adaptation
Authors: Lv, Fengmao
Lin, Guosheng
Liu, Peng
Yang, Guowu
Pan, Sinno Jialin
Duan, Lixin
Keywords: Engineering::Computer science and engineering
Issue Date: 2020
Source: Lv, F., Lin, G., Liu, P., Yang, G., Pan, S. J. & Duan, L. (2020). Weakly-supervised cross-domain road scene segmentation via multi-level curriculum adaptation. IEEE Transactions On Circuits and Systems for Video Technology, 31(9), 3493-3503.
Journal: IEEE Transactions on Circuits and Systems for Video Technology
Abstract: Semantic segmentation, which aims to acquire pixel-level understanding about images, is among the key components in computer vision. To train a good segmentation model for real-world images, it usually requires a huge amount of time and labor effort to obtain sufficient pixel-level annotations of real-world images beforehand. To get rid of such a nontrivial burden, one can use simulators to automatically generate synthetic images that inherently contain full pixel-level annotations and use them to train a segmentation model for the real-world images. However, training with synthetic images usually cannot lead to good performance due to the domain difference between the synthetic images (i.e., source domain) and the real-world images (i.e., target domain). To deal with this issue, a number of unsupervised domain adaptation (UDA) approaches have been proposed, where no labeled real-world images are available. Different from those methods, in this work, we conduct a pioneer attempt by using easy-to-collect image-level annotations for target images to improve the performance of cross-domain segmentation. Specifically, we leverage those image-level annotations to construct curriculums for the domain adaptation problem. The curriculums describe multi-level properties of the target domain, including label distributions over full images, local regions and single pixels. Since image annotations are 'weak' labels compared to pixel annotations for segmentation, we coin this new problem as weakly-supervised cross-domain segmentation. Comprehensive experiments on the GTA5 -> Cityscapes and SYNTHIA -> Cityscapes settings demonstrate the effectiveness of our method over the existing state-of-the-art baselines.
ISSN: 1051-8215
DOI: 10.1109/TCSVT.2020.3040343
Schools: School of Computer Science and Engineering 
Rights: © 2020 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Citations 50

Updated on Sep 30, 2023

Web of ScienceTM
Citations 20

Updated on Oct 2, 2023

Page view(s)

Updated on Oct 3, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.