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.
原文 | 英語 |
---|---|
主出版物標題 | Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 |
發行者 | IEEE Computer Society |
頁面 | 17632-17641 |
頁數 | 10 |
ISBN(電子) | 9781665469463 |
DOIs | |
出版狀態 | 已出版 - 2022 |
對外發佈 | 是 |
事件 | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, 美國 持續時間: 19 06 2022 → 24 06 2022 |
出版系列
名字 | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
卷 | 2022-June |
ISSN(列印) | 1063-6919 |
Conference
Conference | 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 |
---|---|
國家/地區 | 美國 |
城市 | New Orleans |
期間 | 19/06/22 → 24/06/22 |
文獻附註
Publisher Copyright:© 2022 IEEE.