MVP: Multivariate polynomials for conditional generation

Grigorios Chrysos, Yannis Panagakis

Keywords: conditional image generation, generative models, polynomial neural networks

Abstract: Conditional Generative Adversarial Nets (cGANs) have been widely adopted for image generation. cGANs take i) a noise vector and ii) a conditional variable as input. The conditional variable can be discrete (e.g., a class label) or continuous (e.g., an input image) resulting into class-conditional (image) generation and image-to-image translation models, respectively. However, depending on whether the conditional variable is discrete or continuous, various cGANs employ substantially different deep architectures and loss functions for their training. In this paper, we propose a novel framework, called MVP, for conditional data generation. MVP resorts to multivariate polynomials of higher-order and treats in a unified way both discrete and continuous conditional variables. MVP is highly expressive, capturing higher-order auto- and cross-correlations of input variables (noise vector and conditional variable). Tailored sharing schemes are designed between the polynomial’s parameter tensors, which result in simple recursive formulas. MVP can synthesize realistic images in both class-conditional and image-to-image translation tasks even in the absence of activation functions between the layers.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: Conditional data generation is framed as a high-order polynomial expansion of the input.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=Oyv8Liu1_4