资源分类
》 资源 》论文》Generating Images with Perceptual Similarity Metrics based on Deep Networks

Generating Images with Perceptual Similarity Metrics based on Deep Networks

2020-02-07 | |  83 |   39 |   0

Abstract 

We propose a class of loss functions, which we call deep perceptual similarity metrics (DeePSiM), allowing to generate sharp high resolution images from compressed abstract representations. Instead of computing distances in the image space, we compute distances between image features extracted by deep neural networks. This metric reflects perceptual similarity of images much better and, thus, leads to better results. We demonstrate two examples of use cases of the proposed loss: (1) networks that invert the AlexNet convolutional network; (2) a modified version of a variational autoencoder that generates realistic high-resolution random images.

上一篇：Integrated Perception with Recurrent Multi-Task Neural Networks

下一篇：Unsupervised Learning of Spoken Language with Visual Context

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...