Deep Feature Consistent Variational Autoencoder
Xianxu Hou, Linlin Shen, Ke Sun et al. · IEEE Winter Conference on Applications of Computer Vision · 2017
We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the spatial correlation characteristics of the input, thus leading the output to have a more natural visual appearance and better perceptual quality. Based on recent deep learning works such as style transfer, we employ a pre-trained deep convolutional neural network (CNN) and use its hidden features to define a feature perceptual loss for VAE training. Evaluated on the CelebA face dataset, we show that our model produces better results than other methods in the literature. We also show that our method can produce latent vectors that can capture the semantic information of face expressions and can be used to achieve state-of-the-art performance in facial attribute prediction.
Cited by 334 works. doi:10.1109/wacv.2017.131 Open-access PDF
Authors
References
- ImageNet classification with deep convolutional neural networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Adam: A Method for Stochastic Optimization
- ImageNet Large Scale Visual Recognition Challenge
- Fully convolutional networks for semantic segmentation
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
- Scikit-learn: Machine Learning in Python
- Visualizing Data using t-SNE
- GAN(Generative Adversarial Nets)