Hierarchical Variational Autoencoder for Visual Counterfactuals

Autor:	Vercheval, Nicolas, Pizurica, Aleksandra
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Conditional Variational Auto Encoders (VAE) are gathering significant attention as an Explainable Artificial Intelligence (XAI) tool. The codes in the latent space provide a theoretically sound way to produce counterfactuals, i.e. alterations resulting from an intervention on a targeted semantic feature. To be applied on real images more complex models are needed, such as Hierarchical CVAE. This comes with a challenge as the naive conditioning is no longer effective. In this paper we show how relaxing the effect of the posterior leads to successful counterfactuals and we introduce VAEX an Hierarchical VAE designed for this approach that can visually audit a classifier in applications. Comment: 5 pages, 3 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2102.00854 Zobrazit plný text záznamu View this record from Arxiv