论文标题
空间矩池改善神经图像评估
Spatial Moment Pooling Improves Neural Image Assessment
论文作者
论文摘要
近年来，人们普遍关注基于卷积的神经网络（CNN）的盲图质量评估（IQA）。大量作品首先从CNN中提取深度功能。然后，通过空间平均池（SAP）和完全连接的图层来处理这些特征以预测质量。在本文中，我们受到完整参考IQA和纹理功能的启发，我们通过合并高阶矩（例如方差，偏度），将SAP（$ 1^{st} $时刻）扩展到空间矩池（SMP）中。此外，当计算较高矩的梯度时，我们提供了学习友好的归一化来规避数值问题。实验结果表明，仅将SAP升级到SMP可以显着增强基于CNN的盲目IQA方法，并达到最先进的性能状态。
In recent years, there has been widespread attention drawn to convolutional neural network (CNN) based blind image quality assessment (IQA). A large number of works start by extracting deep features from CNN. Then, those features are processed through spatial average pooling (SAP) and fully connected layers to predict quality. Inspired by full reference IQA and texture features, in this paper, we extend SAP ($1^{st}$ moment) into spatial moment pooling (SMP) by incorporating higher order moments (such as variance, skewness). Moreover, we provide learning friendly normalization to circumvent numerical issue when computing gradients of higher moments. Experimental results suggest that simply upgrading SAP to SMP significantly enhances CNN-based blind IQA methods and achieves state of the art performance.
