https://scholars.lib.ntu.edu.tw/handle/123456789/631469
標題: | Learning Multiple Adverse Weather Removal via Two-stage Knowledge Learning and Multi-contrastive Regularization: Toward a Unified Model | 作者: | WEI-TING CHEN Huang, Zhi Kai Tsai, Cheng Che Yang, Hao Hsiang JIAN-JIUN DING SY-YEN KUO |
關鍵字: | Computational photography | Computer vision theory | Low-level vision | Others | 公開日期: | 1-一月-2022 | 卷: | 2022-June | 來源出版物: | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | 摘要: | In this paper, an ill-posed problem of multiple adverse weather removal is investigated. Our goal is to train a model with a 'unified' architecture and only one set of pretrained weights that can tackle multiple types of adverse weathers such as haze, snow, and rain simultaneously. To this end, a two-stage knowledge learning mechanism including knowledge collation (KC) and knowledge examination (KE) based on a multi-teacher and student architecture is proposed. At the KC, the student network aims to learn the comprehensive bad weather removal problem from multiple well-trained teacher networks where each of them is specialized in a specific bad weather removal problem. To accomplish this process, a novel collaborative knowledge transfer is proposed. At the KE, the student model is trained without the teacher networks and examined by challenging pixel loss derived by the ground truth. Moreover, to improve the performance of our training framework, a novel loss function called multi-contrastive knowledge regularization (MCR) loss is proposed. Experiments on several datasets show that our student model can achieve promising results on different bad weather removal tasks simultaneously. The code is available in our project page. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/631469 | ISBN: | 9781665469463 | ISSN: | 10636919 | DOI: | 10.1109/CVPR52688.2022.01713 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。