[论文解读] Single Image Super-resolution with a Parameter Economic Residual-like Convolutional Neural Network

Yudong Liang, Ze Yang+4 more|arXiv (Cornell University)|Mar 23, 2017

Advanced Image Processing Techniques被引用 2

一句话总结

本文提出了一种参数高效的残差式卷积神经网络，用于单图像超分辨率，通过自适应网络深度和跳跃连接缓解梯度消失问题并降低计算成本。该方法在保持视觉质量的同时，实现了最先进的PSNR和SSIM指标，且对残差网络中的激活中心化与集成行为进行了广泛分析。

ABSTRACT

Recent years have witnessed great success of convolutional neural network (CNN) for various problems both in low and high level visions. Especially noteworthy is the residual network which was originally proposed to handle high-level vision problems and enjoys several merits. This paper aims to extend the merits of residual network, such as skip connection induced fast training, for a typical low-level vision problem, i.e., single image super-resolution. In general, the two main challenges of existing deep CNN for supper-resolution lie in the gradient exploding/vanishing problem and large numbers of parameters or computational cost as CNN goes deeper. Correspondingly, the skip connections or identity mapping shortcuts are utilized to avoid gradient exploding/vanishing problem. In addition, the skip connections have naturally centered the activation which led to better performance. To tackle with the second problem, a lightweight CNN architecture which has carefully designed width, depth and skip connections was proposed. In particular, a strategy of gradually varying the shape of network has been proposed for residual network. Different residual architectures for image super-resolution have also been compared. Experimental results have demonstrated that the proposed CNN model can not only achieve state-of-the-art PSNR and SSIM results for single image super-resolution but also produce visually pleasant results. This paper has extended the mmm 2017 oral conference paper with a considerable new analyses and more experiments especially from the perspective of centering activations and ensemble behaviors of residual network.

研究动机与目标

• 解决深度卷积神经网络在单图像超分辨率任务中面临的梯度消失与参数量过高的挑战。
• 将残差网络的优势——特别是跳跃连接与恒等捷径——拓展至超分辨率等低层次视觉任务。
• 设计一种轻量级卷积神经网络架构，通过控制宽度、深度与跳跃连接，降低计算成本而不损失性能。
• 研究激活中心化与残差网络中集成行为的作用，以提升训练稳定性和模型泛化能力。
• 在mmm 2017口头报告论文的基础上，提供更全面的分析与额外实验，重点聚焦于网络架构设计与激活动态特性。

提出的方法

• 提出一种具有渐变变化网络深度的残差式卷积神经网络架构，以平衡表征能力与参数效率。
• 采用跳跃连接（恒等捷径）以稳定训练过程，并缓解深度网络中常见的梯度消失问题。
• 通过精细调优网络宽度与深度，最小化参数量，同时在超分辨率任务中保持高性能。
• 利用恒等映射自然实现激活中心化，提升训练收敛性与模型稳定性。
• 实施一种跨层自适应深度变化策略，根据特征复杂度动态调整表征能力。
• 对比多种残差架构，评估跳跃连接与网络深度对超分辨率性能的影响。

实验结果

研究问题

• RQ1 跳跃连接与恒等捷径在深度卷积神经网络用于单图像超分辨率时，如何影响训练稳定性和性能？
• RQ2 具有可控深度与宽度的轻量级卷积神经网络架构，在保持高性能的前提下，能在多大程度上减少参数量与计算成本？
• RQ3 由跳跃连接引起的激活中心化如何影响超分辨率网络中的模型收敛性与泛化能力？
• RQ4 在不同层中动态调整网络深度对重建高分辨率图像质量有何影响？
• RQ5 残差网络的集成行为如何促进超分辨率任务中的性能提升？

主要发现

• 所提模型在单图像超分辨率基准数据集上实现了最先进的PSNR与SSIM指标。
• 跳跃连接的使用显著提升了训练稳定性，有效缓解了深度网络中的梯度消失问题。
• 由恒等捷径引发的激活中心化带来了更好的收敛性与更强的模型性能。
• 自适应深度变化策略实现了高效的参数利用，同时保持了高质量的图像重建效果。
• 轻量级架构在不牺牲性能的前提下显著降低了计算成本，展现出优异的效率-精度权衡。
• 广泛的消融实验与分析证实，激活中心化与残差网络中的集成行为对超分辨率任务至关重要。