FFA-Net: Feature Fusion Attention Network for Single Image Dehazing

Abstract

In this paper, we propose an end-to-end feature fusion at-tention network (FFA-Net) to directly restore the haze-free image. The FFA-Net architecture consists of three key components:1) A novel Feature Attention (FA) module combines Channel Attention with Pixel Attention mechanism, considering that different channel-wise features contain totally different weighted information and haze distribution is uneven on the different image pixels. FA treats different features and pixels unequally, which provides additional flexibility in dealing with different types of information, expanding the representational ability of CNNs. 2) A basic block structure consists of Local Residual Learning and Feature Attention, Local Residual Learning allowing the less important information such as thin haze region or low-frequency to be bypassed through multiple local residual connections, let main network architecture focus on more effective information. 3) An Attention-based different levels Feature Fusion (FFA) structure, the feature weights are adaptively learned from the Feature Attention (FA) module, giving more weight to important features. This structure can also retain the information of shallow layers and pass it into deep layers.The experimental results demonstrate that our proposed FFA-Net surpasses previous state-of-the-art single image dehazing methods by a very large margin both quantitatively and qualitatively, boosting the best published PSNR metric from 30.23 dB to 36.39 dB on the SOTS indoor test dataset. Code has been made available at GitHub.

Single image dehazing algorithm based on pyramid mutil-scale transposed convolutional network

“…Moreover, to evaluate the generalization of the proposed method in this work, the experiments on several real-world haze images are carried out. All the results are compared with five state-of-the-art dehazing methods: Dark Channel Prior (DCP) (He et al, 2009), DehazeNet (Cai et al, 2016), MSCNN (Ren et al, 2016), AOD-Net (Li et al, 2017) and FFA-Net (Qin et al, 2019).…”

“…They transform the atmospheric scattering model and embed it into the dehazing network, and finally, combine Faster R-CNN (Ren et al, 2015) to quantitatively evaluate the effect of dehazing on the high-level visual task. In (Qin et al, 2019), an imageto-image network named FFA-Net is proposed to restore the haze-free images combined with the attention mechanism. This network uses the Feature Attention (FA) module combined channel attention and pixel attention to flexibly deal with the different features and pixels.…”

Separated Channel Attention Convolutional Neural Network (SC-CNN-Attention) to Identify ADHD in Multi-Site Rs-fMRI Dataset

“…The attention-based network recently was widely applied to deep learning [ 32 , 33 ]. Attention gives the model the ability to distinguish the focus that should be focused on the numerous information, providing an important away to capture more reliable features [ 34 ]. In the first-stage network, the SC-CNN encoders obtained different channel-wise features, which were then concatenated as the input of the attention network.…”

Iterative Residual Network for Image Dehazing

“…Liu et al [10] proposed GridDehazeNet by integrating the attention mechanism into multi-scale estimation. Qin et al [37] proposed an end-to-end feature fusion attention network (FFA-Net), through an attention-based feature fusion structure that can retain shallow information and transfer it to the deep. Dong et al [11] proposed a Multi-Scale Boosted Dehazing Network with dense feature fusion based on the U-Net .…”

“…During training, the indoor synthetic image dataset and outdoor synthetic image dataset are used to train the model separately. The learning rate is set to 0.0001, batchsize is set to 1, epoch is set to 10, and Adam [37] is used as the optimizer. Use Pytorch as the framework and NVIDIA TITAN RTX for training.…”