Contrastive Haze-Aware Learning for Dynamic Remote Sensing Image Dehazing

Author:

Nie Jiangtao1ORCID,Wei Wei1ORCID,Zhang Lei1ORCID,Yuan Jianlong2,Wang Zhibin2ORCID,Li Hao2ORCID

Affiliation:

1. Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi’an, China

2. Alibaba Group, Hangzhou, China

Funder

National Natural Science Foundation of China

Shenzhen Fundamental Research Program

Fundamental Research Funds for the Central Universities

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

General Earth and Planetary Sciences,Electrical and Electronic Engineering

Reference42 articles.

1. CondConv: Conditionally parameterized convolutions for efficient inference;yang;Advances in neural information processing systems,2019

2. Dynamic Convolution: Attention Over Convolution Kernels

3. Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference

4. LambdaNetworks: Modeling long-range interactions without attention;bello;Proc Int Conf Learn Represent,2021

5. Learning Dynamic Routing for Semantic Segmentation

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Phase Learning Based on Interactive Perception for Limited-Sample Residential Area Semantic Segmentation;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. A Remote Sensing Image Dehazing Method Based on Heterogeneous Priors;IEEE Transactions on Geoscience and Remote Sensing;2024

3. IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-Sensing Images;IEEE Transactions on Geoscience and Remote Sensing;2024

4. Robust Haze and Thin Cloud Removal via Conditional Variational Autoencoders;IEEE Transactions on Geoscience and Remote Sensing;2024

5. A Unified Framework for Double-Degradation Remote Sensing Image Restoration Through Saliency-Guided Interaction Learning;IEEE Transactions on Geoscience and Remote Sensing;2024

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3