Multi-view Generative Adversarial Networks
Mickaël Chen, Ludovic Denoyer
Abstract
Learning over multi-view data is a challenging problem with strong practical applications. Most related studies focus on the classification point of view and assume that all the views are available at any time. We consider an extension of this framework in two directions. First, based on the BiGAN model, the Multi-view BiGAN (MV-BiGAN) is able to perform density estimation from multi-view inputs. Second, it can deal with missing views and is able to update its prediction when additional views are provided. We illustrate these properties on a set of experiments over different datasets.
Related Papers
Missing value imputation with adversarial random forests -- MissARF2025-07-213C-FBI: A Combinatorial method using Convolutions for Circle Fitting in Blurry Images2025-07-15Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis2025-07-02Binned semiparametric Bayesian networks2025-06-27Distilling Normalizing Flows2025-06-26EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression2025-06-24SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning2025-06-17Scaling-Up the Pretraining of the Earth Observation Foundation Model PhilEO to the MajorTOM Dataset2025-06-17