Search Results for author: Martin Engelcke

Found 10 papers, 6 papers with code

Universal Approximation of Functions on Sets

no code implementations5 Jul 2021 Edward Wagstaff, Fabian B. Fuchs, Martin Engelcke, Michael A. Osborne, Ingmar Posner

We provide a theoretical analysis of Deep Sets which shows that this universal approximation property is only guaranteed if the model's latent space is sufficiently high-dimensional.

GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

1 code implementation20 Apr 2021 Martin Engelcke, Oiwi Parker Jones, Ingmar Posner

Moreover, object representations are often inferred using RNNs which do not scale well to large images or iterative refinement which avoids imposing an unnatural ordering on objects in an image but requires the a priori initialisation of a fixed number of object representations.

Image Generation Latent Variable Models +4

Reconstruction Bottlenecks in Object-Centric Generative Models

1 code implementation13 Jul 2020 Martin Engelcke, Oiwi Parker Jones, Ingmar Posner

A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision.

Latent Variable Models Object Discovery

On the Limitations of Representing Functions on Sets

no code implementations25 Jan 2019 Edward Wagstaff, Fabian B. Fuchs, Martin Engelcke, Ingmar Posner, Michael Osborne

Recent work on the representation of functions on sets has considered the use of summation in a latent space to enforce permutation invariance.

Gaussian Processes

Cannot find the paper you are looking for? You can Submit a new open access paper.