Fast Approximate Geodesics for Deep Generative Models
arXiv:1812.08284
Abstract
The length of the geodesic between two data points along a Riemannian manifold, induced by a deep generative model, yields a principled measure of similarity. Current approaches are limited to low-dimensional latent spaces, due to the computational complexity of solving a non-convex optimisation problem. We propose finding shortest paths in a finite graph of samples from the aggregate approximate posterior, that can be solved exactly, at greatly reduced runtime, and without a notable loss in quality. Our approach, therefore, is hence applicable to high-dimensional problems, e.g., in the visual domain. We validate our approach empirically on a series of experiments using variational autoencoders applied to image data, including the Chair, FashionMNIST, and human movement data sets.
28th International Conference on Artificial Neural Networks, 2019
References in corpus (7)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference
- Metrics for Deep Generative Models
- Metrics for Probabilistic Geometries
- Active Learning based on Data Uncertainty and Model Sensitivity