Curricular Contrastive Regularization for Physics-Aware Single Image Dehazing
Authors:
Top Cited Papers
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5785-5794
Abstract
Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are non-consensual, as the negatives are usually represented distantly from the clear (i.e., positive) image, leaving the solution space still under-constricted. Moreover, the interpretability of deep dehazing models is underexplored towards the physics of the hazing process. In this paper, we propose a novel curricular contrastive regularization targeted at a consensual contrastive space as opposed to a non-consensual one. Our negatives, which provide better lower-bound constraints, can be assembled from 1) the hazy image, and 2) corresponding restorations by other existing methods. Further, due to the different similarities between the embeddings of the clear image and negatives, the learning difficulty of the multiple components is intrinsically imbalanced. To tackle this issue, we customize a curriculum learning strategy to reweight the importance of different negatives. In addition, to improve the interpretability in the feature space, we build a physics-aware dual-branch unit according to the atmospheric scattering model. With the unit, as well as curricular contrastive regularization, we establish our dehazing network, named C 2 PNet. Extensive experiments demonstrate that our C 2 PNet significantly outperforms state-of-the-art methods, with extreme PSNR boosts of 3.94dB and 1.50dB, respectively, on SOTS-indoor and SOTS-outdoor datasets. Code is available at https://github.com/YuZheng9/C2PNet.Keywords
This publication has 22 references indexed in Scilit:
- Bag of Tricks for Image Classification with Convolutional Neural Networks2019
- Gated Context Aggregation Network for Image Dehazing and Deraining2019
- Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understanding2018
- Densely Connected Pyramid Dehazing Network2018
- AOD-Net: All-in-One Dehazing Network2017
- DehazeNet: An End-to-End System for Single Image Haze RemovalIEEE Transactions on Image Processing, 2016
- FaceNet: A unified embedding for face recognition and clustering2015
- Curriculum learning2009
- Vision in bad weather1999
- Learning and development in neural networks: the importance of starting smallCognition, 1993