ClassSR：通过数据特征加速超分辨率网络的通用框架
ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic
摘要：
我们的目标是在大图像（2K-8 K）上加速超分辨率（SR）网络。在实际应用中，通常将大图像分解为小的子图像。在此基础上，我们发现不同的图像区域具有不同的恢复难度，可以由不同容量的网络进行处理。直观的，平滑的区域比复杂的纹理更容易超级解决。为了利用这一特性，我们可以采用适当的SR网络来处理分解后的不同子图像。在此基础上，我们提出了一种新的解决方案管道- ClassSR，它将分类和SR结合在一个统一的框架中。特别地，它首先使用一个类模块将子图像根据恢复难度分为不同的类，然后应用一个SR模块对不同的类进行SR。类模块是一个传统的分类网络，而SR模块是一个网络容器，它由待加速的SR网络及其简化版本组成。我们进一步介绍了一种新的分类方法，两个损失-类损失和平均损失产生的分类结果。联合训练后，大部分子图像将通过较小的网络，从而可以显着降低计算成本。实验表明，我们的ClassSR可以帮助大多数现有的方法（例如，FSRCNN，CARN，SRResNet，RCAN）在DIV 8 K数据集上节省高达50%的FLOP。这个框架也可以应用于其他低层次的视觉任务。
英文摘要：
We aim at accelerating super-resolution (SR) networks on large images (2K-8K). The large images are usually decomposed into small sub-images in practical usages. Based on this processing, we found that different image regions have different restoration difficulties and can be processed by networks with different capacities. Intuitively, smooth areas are easier to super-solve than complex textures. To utilize this property, we can adopt appropriate SR networks to process different sub-images after the decomposition. On this basis, we propose a new solution pipeline -- ClassSR that combines classification and SR in a unified framework. In particular, it first uses a Class-Module to classify the sub-images into different classes according to restoration difficulties, then applies an SR-Module to perform SR for different classes. The Class-Module is a conventional classification network, while the SR-Module is a network container that consists of the to-be-accelerated SR network and its simplified versions. We further introduce a new classification method with two losses -- Class-Loss and Average-Loss to produce the classification results. After joint training, a majority of sub-images will pass through smaller networks, thus the computational cost can be significantly reduced. Experiments show that our ClassSR can help most existing methods (e.g., FSRCNN, CARN, SRResNet, RCAN) save up to 50% FLOPs on DIV8K datasets. This general framework can also be applied in other low-level vision tasks.
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。
