Understanding the (un)interpretability of natural image distributions using generative models

By Ryen Krusinga, Sohil Shah, Matthias Zwicker, Tom Goldstein, David W. Jacobs. 2019

12 citations recorded by the source corpus.

Probability density estimation is a classical and well studied problem, but standard density estimation methods have historically lacked the power to model complex and high-dimensional image distributions. More recent generative models leverage the power of neural networks to implicitly learn and represent probability models over complex images. We describe methods to extract explicit probability density estimates from GANs, and explore the properties of these image density functions. We perform sanity check experiments to provide evidence that these probabilities are reasonable. However, we also show that density functions of natural images are difficult to interpret and thus limited in use. We study reasons for this lack of interpretability, and show that we can get interpretability back by doing density estimation on latent representations of images.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Cuntai Guan
2. Erico Tjoa
3. Fabien Lotte

Citations in the corpus

• A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “GAN-based Multi-stage PCA [117] X 7 Estimating probability density with deep feature embedding [118] 7 X”