TY - GEN
T1 - Multiple adverse weather removal using adversarial and contrastive learning
AU - Zhang, Yuanfan
AU - Wang, Jinghua
AU - Hu, Liang
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Adverse weather removal is significant and valuable for real-world computer vision systems. Most existing algorithms focus on removing one specific type of weather and rely on paired synthesized weather datasets for training. In this paper, to train a multiple weather removal model with unpaired datasets, we introduce multi-dimension contrastive learning mechanism into generative adversarial networks. Specifically, our method consists of two blocks: multi-channel cycle translation (MCCT) block and multi-dimension contrastive learning (MDCL) block. MCCT is used to preserve the color and structural information and gain informative supervisory signals. MDCL is proposed to discriminate feature distribution among different image domains. Results of extensive experiments show that our method is superior over existing unsupervised methods and maintains a decent performance degradation when adapted to multiple weather removal tasks.
AB - Adverse weather removal is significant and valuable for real-world computer vision systems. Most existing algorithms focus on removing one specific type of weather and rely on paired synthesized weather datasets for training. In this paper, to train a multiple weather removal model with unpaired datasets, we introduce multi-dimension contrastive learning mechanism into generative adversarial networks. Specifically, our method consists of two blocks: multi-channel cycle translation (MCCT) block and multi-dimension contrastive learning (MDCL) block. MCCT is used to preserve the color and structural information and gain informative supervisory signals. MDCL is proposed to discriminate feature distribution among different image domains. Results of extensive experiments show that our method is superior over existing unsupervised methods and maintains a decent performance degradation when adapted to multiple weather removal tasks.
KW - adverse weather removal
KW - contrastive learning
KW - deep learning
KW - generative adversarial networks
KW - unsupervised learning
UR - https://www.scopus.com/pages/publications/85187371885
U2 - 10.1109/SWC57546.2023.10448702
DO - 10.1109/SWC57546.2023.10448702
M3 - 会议稿件
AN - SCOPUS:85187371885
T3 - Proceedings - 2023 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Autonomous and Trusted Vehicles, Scalable Computing and Communications, Digital Twin, Privacy Computing and Data Security, Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PCDS/Metaverse 2023
BT - Proceedings - 2023 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Autonomous and Trusted Vehicles, Scalable Computing and Communications, Digital Twin, Privacy Computing and Data Security, Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PCDS/Metaverse 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th IEEE Smart World Congress, SWC 2023
Y2 - 28 August 2023 through 31 August 2023
ER -