Reconstruction Bottlenecks in Object-Centric Generative Models

07/13/2020
by   Martin Engelcke, et al.
1

A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision. However, these are largely restricted to visually simple images; robust object discovery in real-world sensory datasets remains elusive. To increase the understanding of such inductive biases, we empirically investigate the role of "reconstruction bottlenecks" for scene decomposition in GENESIS, a recent VAE-based model. We show such bottlenecks determine reconstruction and segmentation quality and critically influence model behaviour.

READ FULL TEXT
research
04/18/2022

Inductive Biases for Object-Centric Representations of Complex Textures

Understanding which inductive biases could be useful for the unsupervise...
research
06/27/2020

On the generalization of learning-based 3D reconstruction

State-of-the-art learning-based monocular 3D reconstruction methods lear...
research
05/24/2023

What can generic neural networks learn from a child's visual experience?

Young children develop sophisticated internal models of the world based ...
research
03/21/2022

Generating Fast and Slow: Scene Decomposition via Reconstruction

We consider the problem of segmenting scenes into constituent entities, ...
research
04/20/2021

GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

Advances in object-centric generative models (OCGMs) have culminated in ...
research
04/07/2022

Equivariance Discovery by Learned Parameter-Sharing

Designing equivariance as an inductive bias into deep-nets has been a pr...
research
03/31/2023

Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning

Object-centric learning (OCL) aspires general and compositional understa...

Please sign up or login with your details

Forgot password? Click here to reset