A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection
By Zhihao Chen, Lei Zhu, Liang Wan, Song Wang, Wei Feng, P. Heng. 2020
171 citations recorded by the source corpus.
Existing 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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Dacheng Tao
- Jianping Gou
- S. Maybank
- Baosheng Yu
- Gabriella Csurka
- Jing Zhang
- Charu C. Aggarwal
- Dan Alistarh
In Computer Vision and Pattern Recognition
- Dacheng Tao
- Jianping Gou
- S. Maybank
- Baosheng Yu
- Luc Van Gool
- Trevor Darrell
- Xiaogang Wang
- Ming-Hsuan Yang
Citations in the corpus
- Knowledge Distillation: A Survey (2020, background): “A variety of online knowledge distillation methods have been proposed, especially in the last few years (Zhang et al. 2018b; Chen et al. 2020a; Xie et al. 2019; Anil et al. 2018; Kim et al. 2019b; Zhou et al. 2018; Walawalkar et al. 2020; Wu and Gong 2021; Zhang et al. 2021a).”