Approximate-Analysis-by-Synthesis: Compositional Generative Networks with weak supervision, multi-task consistency and out-of-distribution performance.

Abstract

We propose a new class of generative models, which we call 3D Compositional Generative Networks (CGNs), which perform approximate-an alysis-by-synthesis whose performance is as good as Deep Nets on current benchmarks using standard performance measures (SPMs) but w hich can outperform them on more challenging tasks, such as out-of-distribution testing, multi-task consistently, and robustness to adversarial examiners, while requiring only weak supervision. We are particularly interested in enabling CGNs to detect parts, attri butes, and 3D structures of objects because these abilities will be of great practical use and, in particular for systems that combi ne vision with language and robotics. A key aspect of our research strategy, which exploits the ability of CGNs to perform modal-dom ain-transfer between real and synthetic images is the use of Computer Graphic models not only for representing objects but also to p rovide synthetic stimuli to help train and test them.

Document Details

Document Type
DoD Grant Award
Publication Date
Sep 07, 2021
Source ID
N000142112812

Entities

People

  • Alan Yuille

Organizations

  • Johns Hopkins University
  • Office of Naval Research
  • United States Navy

Tags

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Snow Cover Descriptors for Reptiles and Their Illustrations.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Autonomy
  • Autonomy - Autonomous System Control