APSIPA Transactions on Signal and Information Processing > Vol 12 > Issue 4

FOANet: A Feedback Operation-Attention Network for Single Image Haze Removal

Chia-Lin Liu, University of Washington, USA, Lei Chen, National Yang Ming Chiao Tung University, Taiwan, Ling Lo, National Yang Ming Chiao Tung University, Taiwan, Pin-Jui Huang, National Yang Ming Chiao Tung University, Taiwan, Hong-Han Shuai, National Yang Ming Chiao Tung University, Taiwan, Wen-Huang Cheng, National Yang Ming Chiao Tung University, Taiwan, whcheng@nycu.edu.tw , Ching-Hsuan Wang, Chunghwa Telecom Laboratories, Taiwan, Fan Chou, Chunghwa Telecom Laboratories, Taiwan
 
Suggested Citation
Chia-Lin Liu, Lei Chen, Ling Lo, Pin-Jui Huang, Hong-Han Shuai, Wen-Huang Cheng, Ching-Hsuan Wang and Fan Chou (2023), "FOANet: A Feedback Operation-Attention Network for Single Image Haze Removal", APSIPA Transactions on Signal and Information Processing: Vol. 12: No. 4, e101. http://dx.doi.org/10.1561/116.00000144

Publication Date: 15 May 2023
© 2023 C.-L. Liu et al.
 
Subjects
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 737 times

In this article:
Introduction 
Related Work 
The Proposed FOANet 
Experimental Results 
Conclusions and Future Work 
References 

Abstract

Single image dehazing has become an important vision task for prevailing image degradation caused by detrimental atmosphere transmission conditions. Attention mechanism has been widely utilized in learning based methods to assist the model to discard redundant information and hence boost the performance. However, existing methods are mainly dealing with either channel-wise or pixel-wise attention, which requires much more parameters when the size of feature maps increases. In this paper, we introduce the operation-wise attention in the proposed Feedback Operation-Attention Network (FOANet) to focus on attaining optimal combination of network operations for image dehazing. Specifically, our model consists of two main steps. First, the extracted features of hazy input image are fed to the novel operation-attention block which can adjust the weight of different operations dynamically to produce the optimal processed features. The operation space of an operation-attention block comprises vanilla and dilated convolutions with different kernel sizes along with max pooling and average pooling. Second, we adopt curriculum learning with feedback mechanism to continually refine the features in a recurrent fashion and generate the haze-free image. The experimental results on both synthetic and realistic subsets of RESIDE dataset have demonstrated our method can perform dehazing favorably against other dehazing algorithms.

DOI:10.1561/116.00000144

Companion

APSIPA Transactions on Signal and Information Processing Special Issue - Emerging AI Technologies for Smart Infrastructure
See the other articles that are part of this special issue.