Abstract In recent years, single image super-resolution (SR) methods based on deep convolutional neural networks (CNNs) have made significant progress. However, due to the non-adaptive nature of the convolution operation, they cannot adapt to various characteristics of images, which limits their representational capability and, consequently, results in unnecessarily large model sizes. To address this issue, we propose a novel multi-path adaptive modulation network (MAMNet). Specifically, we propose a multi-path adaptive modulation block (MAMB), which is a lightweight yet effective residual block that adaptively modulates residual feature responses by fully exploiting their information via three paths. The three paths model three types of information suitable for SR: 1) channel-specific information (CSI) using global variance pooling, 2) inter-channel dependencies (ICD) based on the CSI, 3) and channel-specific spatial dependencies (CSD) via depth-wise convolution. We demonstrate that the proposed MAMB is effective and parameter-efficient for image SR than other feature modulation methods. In addition, experimental results show that our MAMNet outperforms most of the state-of-the-art methods with a relatively small number of parameters.

中文翻译：

---

MAMNet：用于图像超分辨率的多路径自适应调制网络

摘要 近年来，基于深度卷积神经网络（CNN）的单幅图像超分辨率（SR）方法取得了重大进展。然而，由于卷积运算的非自适应性，它们不能适应图像的各种特征，这限制了它们的表示能力，从而导致不必要的大模型尺寸。为了解决这个问题，我们提出了一种新颖的多径自适应调制网络（MAMNet）。具体来说，我们提出了一种多路径自适应调制块 (MAMB)，它是一种轻量级但有效的残差块，可通过三个路径充分利用其信息来自适应地调制残差特征响应。这三个路径对适用于 SR 的三类信息进行建模：1) 使用全局方差池化的特定于信道的信息 (CSI)，2) 基于 CSI 的通道间相关性 (ICD)，3) 和通过深度卷积的通道特定空间相关性 (CSD)。我们证明，与其他特征调制方法相比，所提出的 MAMB 对于图像 SR 是有效且参数高效的。此外，实验结果表明，我们的 MAMNet 在参数相对较少的情况下优于大多数最先进的方法。