Evaluating the Generalization Ability of Super-Resolution Networks
This work addresses the problem of evaluating generalization in super-resolution networks for researchers and practitioners in low-level vision, though it is incremental as it introduces a new assessment tool rather than a novel method for super-resolution itself.
The authors tackled the lack of research on generalization ability in super-resolution networks by proposing SRGA, a non-parametric metric to assess it, and benchmarked existing models using a new dataset (PIES), showing that SRGA effectively measures applicability boundaries without requiring learning.
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.