Recently, deep convolutional neural networks (CNNs) have obtained promising results in image processing tasks including super-resolution (SR). However, most CNN-based SR methods treat low-resolution (LR) inputs and features equally across channels, rarely notice the loss of information flow caused by the activation function and fail to leverage the representation ability of CNNs. In this letter, we propose a novel single-image super-resolution (SISR) algorithm named Wider Channel Attention Network (WCAN) for remote sensing images. Firstly, the channel attention mechanism is used to adaptively recalibrate the importance of each channel at the middle of the wider attention block (WAB). Secondly, we propose the Local Memory Connection (LMC) to enhance the information flow. Finally, the features within each WAB are fused to take advantage of the network's representation capability and further improve information and gradient flow. Analytic experiments on a public remote sensing data set (UC Merced) show that our WCAN achieves better accuracy and visual improvements against most state-of-the-art methods.
翻译:最近,在图像处理任务(包括超分辨率(SR))中,深层革命神经网络(CNN)在超分辨率(SR)等图像处理任务方面取得了令人乐观的成果。然而,大多数有线电视新闻网(CNN)的SR方法对低分辨率(LR)的输入和特征在各频道之间一视同仁,很少注意到激活功能造成信息流动的丧失,也没有利用CNN的演示能力。在本信中,我们提议为遥感图像建立一个名为大频道关注网(WCAN)的新颖的单一图像超分辨率算法。首先,频道关注机制用于适应性地调整各频道在更大关注区(WAB)中枢的重要性。第二,我们提议建立地方记忆连接(LMC)以加强信息流动。最后,每个网络内部的功能结合起来,以利用网络的演示能力,进一步改进信息和梯度流。关于公共遥感数据集(UC Merced)的分析实验显示,我们的WCAN在大多数州级方法下实现了更高的准确性和视觉改进。