Deep learning has led to a dramatic leap on Single Image Super-Resolution (SISR) performances in recent years. %Despite the substantial advancement% While most existing work assumes a simple and fixed degradation model (e.g., bicubic downsampling), the research of Blind SR seeks to improve model generalization ability with unknown degradation. Recently, Kong et al pioneer the investigation of a more suitable training strategy for Blind SR using Dropout. Although such method indeed brings substantial generalization improvements via mitigating overfitting, we argue that Dropout simultaneously introduces undesirable side-effect that compromises model's capacity to faithfully reconstruct fine details. We show both the theoretical and experimental analyses in our paper, and furthermore, we present another easy yet effective training strategy that enhances the generalization ability of the model by simply modulating its first and second-order features statistics. Experimental results have shown that our method could serve as a model-agnostic regularization and outperforms Dropout on seven benchmark datasets including both synthetic and real-world scenarios.

翻译：深度学习近年来推动了单图像超分辨率（Single Image Super-Resolution, SISR）性能的显著飞跃。尽管大多数现有研究假设简单且固定的退化模型（例如双三次下采样），盲超分辨率（Blind SR）研究旨在提升模型对未知退化的泛化能力。近期，Kong等人开创性地探索了一种利用Dropout更适合盲超分辨率的训练策略。尽管该方法通过缓解过拟合确实带来了显著的泛化提升，但我们认为Dropout同时引入了不良副作用，削弱了模型忠实重建精细细节的能力。我们在论文中展示了理论和实验分析，并进一步提出了一种简单而有效的训练策略——通过调节模型的一阶和二阶特征统计量来增强泛化能力。实验结果表明，我们的方法可作为模型无关的正则化手段，在包含合成与真实场景的七个基准数据集上优于Dropout。