Can I read Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing on EtoBox?

Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing by Ye, Tian; Chen, ErKang; Huang, XinRui; Chen, Peng is a scholarly article available to read on EtoBox.

What is Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing about?

This paper proposes an end-to-end Efficient Re-parameterizationResidual Attention Network(ERRA-Net) to directly restore the nonhomogeneous hazy image. The contribution of this paper mainly has the following three aspects: 1) A novel Multi-branch Attention (MA) block. The spatial attention mechanism better reconstructs high-frequency features, and the channel attention mechanism treats the features of different channels differently. Multi-branch structure dramatically improves the representation ability of the model and can be changed into a single path structure after re-parameterization to speed up the process of inference. Local Residual Connection allows the low-frequency information in the nonhomogeneous area to pass through the block without processing so that the block can focus on detailed features. 2) A lightweight network structure. We use cascaded MA blocks to extract high-frequency features step by step, and the Multi-layer attention fusion tail combines the shallow and deep features of the model to get the residual of the clean image finally. 3)We propose two novel loss functions to help reconstruct the hazy image ColorAttenuation loss and Laplace Pyramid loss. ERRA-Net

Author

Ye, Tian; Chen, ErKang; Huang, XinRui; Chen, Peng

Published

2021

Language

EN