用于单图像超分辨率的深度自适应推理网络
Deep Adaptive Inference Networks for Single Image Super-Resolution
摘要：
近年来，由于深度卷积神经网络（CNN）的部署，单图像超分辨率（SISR）取得了巨大进展。对于大多数现有方法，每个SISR模型的计算成本与本地图像内容，硬件平台和应用场景无关。尽管如此，内容和资源自适应模型是更可取的，这是令人鼓舞的应用更简单，更有效的网络，更容易的区域与较少的细节和有限的效率约束的场景。在本文中，我们通过利用深度SISR自适应推理网络（AdaDSR）来解决这个问题。特别是，我们的AdaDSR涉及一个SISR模型作为骨干和一个轻量级的适配器模块，该模块将图像特征和资源约束作为输入，并预测本地网络深度的地图。然后可以在有效稀疏卷积的支持下执行自适应推理，其中根据其预测深度在给定位置处仅执行骨干中的一小部分层。网络学习可以表述为重构和网络深度损失的联合优化。在推理阶段，可以灵活地调整平均深度以满足一系列效率约束。实验证明了我们的AdaDSR的有效性和适应性，与它的同行（例如，EDSR和RCAN）。
英文摘要：
Recent years have witnessed tremendous progress in single image super-resolution (SISR) owing to the deployment of deep convolutional neural networks (CNNs). For most existing methods, the computational cost of each SISR model is irrelevant to local image content, hardware platform and application scenario. Nonetheless, content and resource adaptive model is more preferred, and it is encouraging to apply simpler and efficient networks to the easier regions with less details and the scenarios with restricted efficiency constraints. In this paper, we take a step forward to address this issue by leveraging the adaptive inference networks for deep SISR (AdaDSR). In particular, our AdaDSR involves an SISR model as backbone and a lightweight adapter module which takes image features and resource constraint as input and predicts a map of local network depth. Adaptive inference can then be performed with the support of efficient sparse convolution, where only a fraction of the layers in the backbone is performed at a given position according to its predicted depth. The network learning can be formulated as the joint optimization of reconstruction and network depth losses. In the inference stage, the average depth can be flexibly tuned to meet a range of efficiency constraints. Experiments demonstrate the effectiveness and adaptability of our AdaDSR in contrast to its counterparts (e.g., EDSR and RCAN).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
