Perceptual Gradient Networks

Abstract

Many applications of deep learning for image generation use perceptual losses for either training or fine-tuning of the generator networks. The use of perceptual loss however incurs repeated forward-backward passes in a large image classification network as well as a considerable memory overhead required to store the activations of this network. It is therefore desirable or sometimes even critical to get rid of these overheads. In this work, we propose a way to train generator networks using approximations of perceptual loss that are computed without forward-backward passes. Instead, we use a simpler perceptual gradient network that directly synthesizes the gradient field of a perceptual loss. We introduce the concept of proxy targets, which stabilize the predicted gradient, meaning that learning with it does not lead to divergence or oscillations. In addition, our method allows interpretation of the predicted gradient, providing insight into the internals of perceptual loss and suggesting potential ways to improve it in future work.

arXiv comment28 pages, 15 figures, 8 tables

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Distilling the Knowledge in a Neural Network
• Deep Residual Learning for Image Recognition
• VoxCeleb2: Deep Speaker Recognition
• Do Deep Nets Really Need to be Deep?
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs
• Understanding Synthetic Gradients and Decoupled Neural Interfaces