Learning Multiple Adverse Weather Removal via Two-stage Knowledge Learning and Multi-contrastive Regularization: Toward a Unified Model

Wei Ting Chen, Zhi Kai Huang, Cheng Che Tsai, Hao Hsiang Yang, Jian Jiun Ding, Sy Yen Kuo

研究成果: 圖書/報告稿件的類型會議稿件同行評審

113 引文 斯高帕斯(Scopus)

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
事件2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, 美國
持續時間: 19 06 202224 06 2022

出版系列

名字Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
2022-June
ISSN(列印)1063-6919

Conference

Conference2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
國家/地區美國
城市New Orleans
期間19/06/2224/06/22

文獻附註

Publisher Copyright:
© 2022 IEEE.

指紋

深入研究「Learning Multiple Adverse Weather Removal via Two-stage Knowledge Learning and Multi-contrastive Regularization: Toward a Unified Model」主題。共同形成了獨特的指紋。

引用此