Mixed-order channel attention network for single image super-resolution reconstruction
YAO Lu1, SONG Huihui2, ZHANG Kaihua1
1. Jiangsu Key Laboratory of Big Data Analysis Technology(Nanjing University of Information Science and Technology), Nanjing Jiangsu 210044 China; 2. Collaborative Innovation Center on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing Jiangsu 210044, China
Abstract：For the current channel attention mechanism used for super-resolution reconstruction, there are problems that the attention prediction destroys the direct corresponding relationship between each channel and its weight and the mechanism only considers the first-order or second-order channel attention without comprehensive consideration of the advantage complementation. Therefore, a mixed-order channel attention network for image super-resolution reconstruction was proposed. First of all, by using the local cross-channel interaction strategy, increase and reduction in channel dimension used by the first-order and second-order channel attention models were changed into a fast one-dimensional convolution with kernel k, which not only makes the channel attention prediction more direct and accurate but makes the resulting model simpler than before. Besides, the improved first and second-order channel attention models above were adopted to comprehensively take the advantages of channel attentions of different orders, thus improving network discrimination. Experimental results on the benchmark datasets show that compared with the existing super-resolution algorithms, the proposed method has the best recovered texture details and high frequency information of the reconstructed images and the Perceptual Indictor (PI) on Set5 and BSD100 datasets are increased by 0.3 and 0.1 on average respectively. It shows that this network is more accurate in predicting channel attention and comprehensively uses channel attentions of different orders, so as to improve the performance.
[1] 欧阳宁, 梁婷, 林乐平. 基于自注意力网络的图像超分辨率重建[J]. 计算机应用,2019,39(8):2391-2395.(OUYANG N, LIANG T,LIN L P. Self-attention network based image superresolution[J]. Journal of Computer Applications,2019,39(8):2391-2395.) [2] DONG C,LOY C C,HE K,at al. Image super-resolution using deep convolutional network[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(2):295-307. [3] HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778. [4] KIM J,LEE J K,LEE K M. Accurate image super-resolution using very deep convolutional networks[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2016:1646-1654. [5] ZHANG Y,LI K,LI K,et al. Image super-resolution using very deep residual channel attention networks[C]//Proceedings of the 2018 European Conference on Computer Vision,LNCS 11211. Cham:Springer,2018:294-310. [6] ITTI L,KOCH C,NIEBUR E. A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(11):1254-1259. [7] HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[EB/OL].[2017-06-05]. https://arxiv.org/pdf/1709.01507.pdf. [8] DAI T,CAI J,ZHANG Y,et al. Second-order attention network for single image super-resolution[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2019:11057-11066. [9] SHI W,CABALLERO J,HUSZÁR F,et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2016:1874-1883. [10] WANG Q,WU B,ZHU P,et al. ECA-Net:efficient channel attention for deep convolutional neural networks[EB/OL].[2019-10-08]. https://arxiv.org/pdf/1910.03151.pdf. [11] VU T,LUU T M,YOO C D. Perception-enhanced image superresolution via relativistic generative adversarial networks[C]//Proceedings of the 2018 European Conference on Computer Vision,LNCS 11133. Cham:Springer,2018:98-113. [12] AGUSTSSON E,TIMOFTE R. NTIRE 2017 challenge on single image super-resolution:dataset and study[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway:IEEE,2017:1122-1131. [13] BLAU Y,MICHAELI T. The perception-distortion tradeoff[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2018:6228-6237. [14] MA C,YANG C Y,YANG X,et al. Learning a no-reference quality metric for single-image super-resolution[J]. Computer Vision and Image Understanding,2017,158:1-16. [15] MITTAL A,SOUNDARARAJAN R,BOVIK A C. Making a "completely blind" image quality analyzer[J]. IEEE Signal Processing Letters,2013,20(3):209-212. [16] KEYS R. Cubic convolution interpolation for digital image processing[J]. IEEE Transactions on Acoustics,Speech,and Signal Processing,1981,29(6):1153-1160. [17] LIM B,SON S,KIM H,et al. Enhanced deep residual networks for single image super-resolution[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway:IEEE,2017:1132-1440. [18] LEDIG C,THEIS L,HUSZAR F,et al. Photo-realistic single image super-resolution using a generate adversarial network[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway,NJ:IEEE,2017:105-114. [19] SAJJADI M,SCHÖLKOPF B,HIRSCH M. EnhanceNet:single image super-resolution through automated texture synthesis[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE,2017:4501-4510.
2020, Vol. 40 
