Autoencoding Conditional Neural Processes for Representation Learning

arXiv:2305.18485v2 Announce Type: replace
Abstract: Conditional neural processes (CNPs) are a flexible and efficient family of models that learn to learn a stochastic process from data. They have seen particular application in contextual image completion - observing pixel values at some locations to predict a distribution over values at other unobserved locations. However, the choice of pixels in learning CNPs is typically either random or derived from a simple statistical measure (e.g. pixel variance). Here, we turn the problem on …

abstract application arxiv cs.ai cs.lg data distribution family image learn locations pixel process processes representation representation learning stochastic stochastic process type values