A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection
Other conference paper

Times Cited
Web of Science0WOS source URL (as at 11/04/2021) Click here for the latest count
Altmetrics Information

Other information
AbstractExisting shadow detection methods suffer from an intrinsic limitation in relying on limited labeled datasets, and they may produce poor results in some complicated situations. To boost the shadow detection performance, this paper presents a multi-task mean teacher model for semi-supervised shadow detection by leveraging unlabeled data and exploring the learning of multiple information of shadows simultaneously. To be specific, we first build a multi-task baseline model to simultaneously detect shadow regions, shadow edges, and shadow count by leveraging their complementary information and assign this baseline model to the student and teacher network. After that, we encourage the predictions of the three tasks from the student and teacher networks to be consistent for computing a consistency loss on unlabeled data, which is then added to the supervised loss on the labeled data from the predictions of the multi-task baseline model. Experimental results on three widely-used benchmark datasets show that our method consistently outperforms all the compared state-of- the-art methods, which verifies that the proposed network can effectively leverage additional unlabeled data to boost the shadow detection performance.
All Author(s) ListZhihao Chen, Lei Zhu, Liang Wan, Song Wang, Wei Feng, Pheng-Ann Heng
Name of Conference2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020
Start Date of Conference13/06/2020
End Date of Conference19/06/2020
Place of ConferenceVirtual
Country/Region of ConferenceUnited States of America
Proceedings Title2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020
PublisherIEEE Xplore
Pages5611 - 5620
LanguagesEnglish-United Kingdom

Last updated on 2021-11-04 at 23:37