Generating Unobserved Alternatives

11/03/2020
by   Shichong Peng, et al.
0

We consider problems where multiple predictions can be considered correct, but only one of them is given as supervision. This setting differs from both the regression and class-conditional generative modelling settings: in the former, there is a unique observed output for each input, which is provided as supervision; in the latter, there are many observed outputs for each input, and many are provided as supervision. Applying either regression methods and conditional generative models to the present setting often results in a model that can only make a single prediction for each input. We explore several problems that have this property and develop an approach that can generate multiple high-quality predictions given the same input. As a result, it can be used to generate high-quality outputs that are different from the observed output.

READ FULL TEXT

page 13

page 14

page 15

page 16

page 17

page 18

page 19

page 20

research
03/16/2023

PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision

Impressive progress in generative models and implicit representations ga...
research
09/30/2022

Out-of-Distribution Detection and Selective Generation for Conditional Language Models

Machine learning algorithms typically assume independent and identically...
research
01/17/2019

Attentive Neural Processes

Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by le...
research
12/07/2021

CG-NeRF: Conditional Generative Neural Radiance Fields

While recent NeRF-based generative models achieve the generation of dive...
research
05/30/2019

Structured Output Learning with Conditional Generative Flows

Traditional structured prediction models try to learn the conditional li...
research
06/10/2015

Data Generation as Sequential Decision Making

We connect a broad class of generative models through their shared relia...
research
06/08/2018

Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations

Many structured prediction problems (particularly in vision and language...

Please sign up or login with your details

Forgot password? Click here to reset