College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China.
School of Electrical Engineering, Anhui Polytechnic University, Wuhu 241000, China.
Sensors (Basel). 2022 Jul 26;22(15):5586. doi: 10.3390/s22155586.
With the development of deep learning, considerable progress has been made in image restoration. Notably, many state-of-the-art single image super-resolution (SR) methods have been proposed. However, most of them contain many parameters, which leads to a significant amount of calculation consumption in the inference phase. To make current SR networks more lightweight and resource-friendly, we present a convolution neural network with the proposed selective channel processing strategy (SCPN). Specifically, the selective channel processing module (SCPM) is first designed to dynamically learn the significance of each channel in the feature map using a channel selection matrix in the training phase. Correspondingly, in the inference phase, only the essential channels indicated by the channel selection matrixes need to be further processed. By doing so, we can significantly reduce the parameters and the calculation consumption. Moreover, the differential channel attention (DCA) block is proposed, which takes into consideration the data distribution of the channels in feature maps to restore more high-frequency information. Extensive experiments are performed on the natural image super-resolution benchmarks (i.e., Set5, Set14, B100, Urban100, Manga109) and remote-sensing benchmarks (i.e., UCTest and RESISCTest), and our method achieves superior results to other state-of-the-art methods. Furthermore, our method keeps a slim size with fewer than 1 M parameters, which proves the superiority of our method. Owing to the proposed SCPM and DCA, our SCPN model achieves a better trade-off between calculation cost and performance in both general and remote-sensing SR applications, and our proposed method can be extended to other computer vision tasks for further research.
随着深度学习的发展，图像恢复取得了相当大的进展。值得注意的是，已经提出了许多最先进的单图像超分辨率 (SR) 方法。然而，它们中的大多数都包含许多参数，这导致在推理阶段会消耗大量的计算资源。为了使当前的 SR 网络更加轻量级和资源友好，我们提出了一种具有所提出的选择性信道处理策略 (SCPN) 的卷积神经网络。具体来说，首先设计选择性信道处理模块 (SCPM)，以便在训练阶段使用信道选择矩阵动态学习特征图中每个信道的重要性。相应地，在推理阶段，仅需进一步处理由信道选择矩阵指示的基本信道。通过这样做，我们可以显著减少参数和计算消耗。此外，提出了差分通道注意力 (DCA) 块，它考虑了特征图中通道的数据分布，以恢复更多的高频信息。在自然图像超分辨率基准 (即 Set5、Set14、B100、Urban100、Manga109) 和遥感基准 (即 UCTest 和 RESISCTest) 上进行了广泛的实验，我们的方法优于其他最先进的方法。此外，我们的方法保持了小于 1M 参数的苗条尺寸，证明了我们方法的优越性。由于提出的 SCPM 和 DCA，我们的 SCPN 模型在一般和遥感 SR 应用中在计算成本和性能之间实现了更好的权衡，并且我们提出的方法可以扩展到其他计算机视觉任务以进行进一步研究。
