The use of $\ell _{p}$ (p = 1,2) norms has largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess the loss of visual information, these simple norms are not very consistent with human perception. Here, we describe a different “proximal” approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, broadly termed ProxIQA, which mimics the perceptual model while serving as a loss layer of the network. We experimentally demonstrate how this optimization framework can be applied to train an end-to-end optimized image compression network. By building on top of an existing deep image compression model, we are able to demonstrate a bitrate reduction of as much as 31% over MSE optimization, given a specified perceptual quality (VMAF) level.

中文翻译：

---

ProxIQA：一种用于学习图像压缩感知优化的代理方法

指某东西的用途 $ \ ell _ {p} $ （p = 1,2）规范由于其简单性和分析性而在很大程度上控制了神经网络的损耗。但是，当用于评估视觉信息的丢失时，这些简单的规范与人类的感知并不一致。在这里，我们描述了一种针对定量感知模型优化图像分析网络的不同“近端”方法。具体来说，我们构建了一个代理网络，广泛称为ProxIQA，它模仿感知模型，同时充当网络的损失层。我们通过实验演示了如何将此优化框架应用于训练端到端的优化图像压缩网络。通过在现有的深度图像压缩模型之上构建，我们可以证明与MSE优化相比，比特率降低了多达31％，