CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation
Abstract
Problems such as predicting a new shading field (Y) for an image (X) are ambiguous: many very distinct solutions are good. Representing this ambiguity requires building a conditional model P(Y|X) of the prediction, conditioned on the image. Such a model is difficult to train, because we do not usually have training data containing many different shadings for the same image. As a result, we need different training examples to share data to produce good models. This presents a danger we call "code space collapse" - the training procedure produces a model that has a very good loss score, but which represents the conditional distribution poorly. We demonstrate an improved method for building conditional models by exploiting a metric constraint on training data that prevents code space collapse. We demonstrate our model on two example tasks using real data: image saturation adjustment, image relighting. We describe quantitative metrics to evaluate ambiguous generation results. Our results quantitatively and qualitatively outperform different strong baselines.
Cite
@article{arxiv.1612.00132,
title = {CDVAE: Co-embedding Deep Variational Auto Encoder for Conditional Variational Generation},
author = {Jiajun Lu and Aditya Deshpande and David Forsyth},
journal= {arXiv preprint arXiv:1612.00132},
year = {2017}
}