论文标题
评估超分辨率网络的概括能力
Evaluating the Generalization Ability of Super-Resolution Networks
论文作者
论文摘要
性能和概括能力是评估深度学习模型的两个重要方面。但是，目前不存在对超分辨率（SR）网络的概括能力的研究。评估深层模型的概括能力不仅有助于我们了解其内在机制，而且还使我们能够定量测量其适用性边界，这对于不受限制的现实世界应用很重要。为此，我们首次尝试针对SR网络（即SRGA）提出概括评估指数。 SRGA利用了深网的内部特征的统计特征来衡量概括能力。特别是，它是一个非参数和非学习度量的指标。为了更好地验证我们的方法，我们收集了一个基于补丁的图像评估集（PIE），其中包括合成图像和现实世界图像，涵盖了广泛的降级。使用SRGA和PIES数据集，我们将现有的SR模型基于概括能力进行基准测试。这项工作为低级视觉中的模型概括提供了见解和工具。
Performance and generalization ability are two important aspects to evaluate the deep learning models. However, research on the generalization ability of Super-Resolution (SR) networks is currently absent. Assessing the generalization ability of deep models not only helps us to understand their intrinsic mechanisms, but also allows us to quantitatively measure their applicability boundaries, which is important for unrestricted real-world applications. To this end, we make the first attempt to propose a Generalization Assessment Index for SR networks, namely SRGA. SRGA exploits the statistical characteristics of the internal features of deep networks to measure the generalization ability. Specially, it is a non-parametric and non-learning metric. To better validate our method, we collect a patch-based image evaluation set (PIES) that includes both synthetic and real-world images, covering a wide range of degradations. With SRGA and PIES dataset, we benchmark existing SR models on the generalization ability. This work provides insights and tools for future research on model generalization in low-level vision.
