Lune

CVPR2021Top-tier venue

Contrastive Learning for Compact Single Image Dehazing

Haiyan Wu, Yanyun Qu, Shaohui Lin, Jian Zhou, Ruizhi Qiao, Zhizhong Zhang, Yuan Xie, Lizhuang Ma

Abstract

Single image dehazing is a challenging ill-posed problem due to the severe information degeneration. However, existing deep learning based dehazing methods only adopt clear images as positive samples to guide the training of dehazing network while negative information is unexploited. Moreover, most of them focus on strengthening the dehazing network with an increase of depth and width, leading to a significant requirement of computation and memory. In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively. CR ensures that the restored image is pulled to closer to the clear image and pushed to far away from the hazy image in the representation space. Furthermore, considering trade-off between performance and memory storage, we develop a compact dehazing network based on autoencoder-like (AE) framework. It involves an adaptive mixup operation and a dynamic feature enhancement module, which can benefit from preserving information flow adaptively and expanding the receptive field to improve the network's transformation capability, respectively. We term our dehazing network with autoencoder and contrastive regularization as AECR-Net. The extensive experiments on synthetic and real-world datasets demonstrate that our AECR-Net surpass the state-of-the-art approaches. The code is released in https://github. com/GlassyWu/AECR-Net .

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

93 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Image Dehazing Transformer with Transmission-Aware 3D Position Embedding cites GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing
  • Image Dehazing Transformer with Transmission-Aware 3D Position Embedding cites FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
  • A Simple Framework for Contrastive Learning of Visual Representations cites Data-Efficient Image Recognition with Contrastive Predictive Coding
  • MAXIM: Multi-Axis MLP for Image Processing cites GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing
  • MAXIM: Multi-Axis MLP for Image Processing cites FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
  • Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning cites A Simple Framework for Contrastive Learning of Visual Representations
  • Artistic Style Transfer with Internal-external Learning and Contrastive Learning cites A Simple Framework for Contrastive Learning of Visual Representations
  • All-In-One Image Restoration for Unknown Corruption cites A Simple Framework for Contrastive Learning of Visual Representations
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers93

  1. MAXIM: Multi-Axis MLP for Image ProcessingZhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang et al.CVPR 2022 · 550 citations
  2. Image Dehazing Transformer with Transmission-Aware 3D Position EmbeddingChunle Guo, Qixin Yan, Saeed Anwar, Runmin Cong et al.CVPR 2022 · 464 citations
  3. TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather ConditionsJeya Maria Jose Valanarasu, Rajeev Yasarla, Vishal M. PatelCVPR 2022 · 350 citations
  4. All-In-One Image Restoration for Unknown CorruptionBoyun Li, Xiao Liu, Peng Hu, Zhongqin Wu et al.CVPR 2022 · 338 citations
  5. Artistic Style Transfer with Internal-external Learning and Contrastive LearningHaibo Chen, Lei Zhao, Zhizhong Wang, Huiming Zhang et al.NeurIPS 2021 · 243 citations

Builds on8

  1. A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 24,064 citations
  2. Bootstrap Your Own Latent - A New Approach to Self-Supervised LearningJean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec et al.NeurIPS 2020 · 9,171 citations
  3. FFA-Net: Feature Fusion Attention Network for Single Image DehazingXu Qin, Zhilin Wang, Yuanchao Bai, Xiaodong Xie et al.AAAI 2020 · 1,828 citations
  4. Data-Efficient Image Recognition with Contrastive Predictive CodingOlivier J. HénaffICML 2020 · 1,553 citations
  5. GridDehazeNet: Attention-Based Multi-Scale Network for Image DehazingXiaohong Liu, Yongrui Ma, Zhihao Shi, Jun ChenICCV 2019 · 1,015 citations

Related papers

  1. Curricular Contrastive Regularization for Physics-Aware Single Image DehazingYu Zheng, Jiahui Zhan, Shengfeng He, Junyu Dong et al.CVPR 2023
  2. DehazeFlow: Multi-scale Conditional Flow Network for Single Image DehazingHongyu Li, Jia Li, Dong Zhao, Long XuACM MM 2021 · 49 citations
  3. ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image DehazingZhongze Wang, Haitao Zhao, Jingchao Peng, Lujian Yao et al.CVPR 2024 · 24 citations
  4. PDD-GAN: Prior-based GAN Network with Decoupling Ability for Single Image DehazingXiaoxuan Chai, Junchi Zhou, Hang Zhou, Jui-Hsin LaiACM MM 2022 · 7 citations
  5. Depth Information Assisted Collaborative Mutual Promotion Network for Single Image DehazingYafei Zhang, Shen Zhou, Huafeng LiCVPR 2024 · 101 citations
Dusk over the sea between two cliffs drawn in fine vertical lines