Conditional Generative Modeling via Learning the Latent Space

10/07/2020
by   Sameera Ramasinghe, et al.
12

Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings. We propose a novel general-purpose framework for conditional generation in multimodal spaces, that uses latent variables to model generalizable learning patterns while minimizing a family of regression cost functions. At inference, the latent variables are optimized to find optimal solutions corresponding to multiple output modes. Compared to existing generative solutions, in multimodal spaces, our approach demonstrates faster and stable convergence, and can learn better representations for downstream tasks. Importantly, it provides a simple generic model that can beat highly engineered pipelines tailored using domain expertise on a variety of tasks, while generating diverse outputs. Our codes will be released.

READ FULL TEXT

page 22

page 23

page 25

page 30

page 31

page 32

page 33

page 36

research
07/25/2020

Modal Uncertainty Estimation via Discrete Latent Representation

Many important problems in the real world don't have unique solutions. I...
research
07/20/2020

Learning latent representations across multiple data domains using Lifelong VAEGAN

The problem of catastrophic forgetting occurs in deep learning models tr...
research
12/06/2018

Verification of deep probabilistic models

Probabilistic models are a critical part of the modern deep learning too...
research
06/07/2023

Multi-modal Latent Diffusion

Multi-modal data-sets are ubiquitous in modern applications, and multi-m...
research
10/09/2021

Discriminative Multimodal Learning via Conditional Priors in Generative Models

Deep generative models with latent variables have been used lately to le...
research
11/25/2020

How to train your conditional GAN: An approach using geometrically structured latent manifolds

Conditional generative modeling typically requires capturing one-to-many...
research
12/23/2014

Learning Non-deterministic Representations with Energy-based Ensembles

The goal of a generative model is to capture the distribution underlying...

Please sign up or login with your details

Forgot password? Click here to reset