no code implementations • 24 Jun 2024 • Andrew Draganov, Sharvaree Vadgama, Erik J. Bekkers

We show that the gradient of the cosine similarity between two points goes to zero in two under-explored settings: (1) if a point has large magnitude or (2) if the points are on opposite ends of the latent space.

no code implementations • 10 Jun 2024 • David M. Knigge, David R. Wessels, Riccardo Valperga, Samuele Papa, Jan-Jakob Sonke, Efstratios Gavves, Erik J. Bekkers

Recently, Conditional Neural Fields (NeFs) have emerged as a powerful modelling paradigm for PDEs, by learning solutions as flows in the latent space of the Conditional NeF.

no code implementations • 5 Jun 2024 • Veljko Kovač, Erik J. Bekkers, Pietro Liò, Floor Eijkelboom

This paper introduces E(n) Equivariant Message Passing Cellular Networks (EMPCNs), an extension of E(n) Equivariant Graph Neural Networks to CW-complexes.

1 code implementation • NeurIPS 2023 • Miltiadis Kofinas, Erik J. Bekkers, Naveen Shankar Nagaraja, Efstratios Gavves

Systems of interacting objects often evolve under the influence of field effects that govern their dynamics, yet previous works have abstracted away from such effects, and assume that systems evolve in a vacuum.

1 code implementation • 7 Aug 2023 • Artem Moskalev, Anna Sepliarskaia, Erik J. Bekkers, Arnold Smeulders

We demonstrate that even when a network learns to correctly classify samples on a group orbit, the underlying decision-making in such a model does not attain genuine invariance.

no code implementations • 22 Jul 2023 • Putri A. van der Linden, David W. Romero, Erik J. Bekkers

As a result, operations that rely on neighborhood information scale much worse for point clouds than for grid data, specially for large inputs and large neighborhoods.

1 code implementation • 24 Jun 2023 • Thijs P. Kuipers, Erik J. Bekkers

Motivated by the recent work on separable group convolutions, we devise a SE(3) group convolution kernel separated into a continuous SO(3) (rotation) kernel and a spatial kernel.

1 code implementation • 3 May 2023 • Yeskendir Koishekenov, Erik J. Bekkers

The flexibility and effectiveness of message passing based graph neural networks (GNNs) induced considerable advances in deep learning on graph-structured data.

1 code implementation • 25 Jan 2023 • David M. Knigge, David W. Romero, Albert Gu, Efstratios Gavves, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn, Jan-Jakob Sonke

Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data.

1 code implementation • 7 Jun 2022 • David W. Romero, David M. Knigge, Albert Gu, Erik J. Bekkers, Efstratios Gavves, Jakub M. Tomczak, Mark Hoogendoorn

The use of Convolutional Neural Networks (CNNs) is widespread in Deep Learning due to a range of desirable model properties which result in an efficient and effective machine learning framework.

2 code implementations • NeurIPS 2021 • Hugo Aguettaz, Erik J. Bekkers, Michaël Defferrard

Surfing on the success of graph- and group-based neural networks, we take advantage of the recent developments in the geometric deep learning field to derive a new approach to exploit any anisotropies in data.

no code implementations • 14 Nov 2021 • Jan Zuiderveld, Marco Federici, Erik J. Bekkers

The high temporal resolution of audio and our perceptual sensitivity to small irregularities in waveforms make synthesizing at high sampling rates a complex and computationally intensive task, prohibiting real-time, controllable synthesis within many approaches.

1 code implementation • 25 Oct 2021 • David M. Knigge, David W. Romero, Erik J. Bekkers

In addition, thanks to the increase in computational efficiency, we are able to implement G-CNNs equivariant to the $\mathrm{Sim(2)}$ group; the group of dilations, rotations and translations.

Ranked #1 on Rotated MNIST on Rotated MNIST

1 code implementation • ICLR 2022 • David W. Romero, Robert-Jan Bruintjes, Jakub M. Tomczak, Erik J. Bekkers, Mark Hoogendoorn, Jan C. van Gemert

In this work, we propose FlexConv, a novel convolutional operation with which high bandwidth convolutional kernels of learnable kernel size can be learned at a fixed parameter cost.

1 code implementation • ICLR 2022 • David W. Romero, Anna Kuzina, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn

Convolutional networks are unable to handle sequences of unknown size and their memory horizon must be defined a priori.

Ranked #5 on Sequential Image Classification on Sequential MNIST

1 code implementation • 9 Jun 2020 • David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn

In this work, we fill this gap by leveraging the symmetries inherent to time-series for the construction of equivariant neural network.

1 code implementation • 20 Feb 2020 • Maxime W. Lafarge, Erik J. Bekkers, Josien P. W. Pluim, Remco Duits, Mitko Veta

This study is focused on histopathology image analysis applications for which it is desirable that the arbitrary global orientation information of the imaged tissues is not captured by the machine learning models.

Ranked #5 on Breast Tumour Classification on PCam

1 code implementation • ICML 2020 • David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn

Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e. g., relative positions and poses).

2 code implementations • ICLR 2020 • Erik J. Bekkers

The impact and potential of our approach is studied on two benchmark datasets: cancer detection in histopathology slides in which rotation equivariance plays a key role and facial landmark localization in which scale equivariance is important.

1 code implementation • 10 Apr 2018 • Erik J. Bekkers, Maxime W. Lafarge, Mitko Veta, Koen AJ Eppenhof, Josien PW Pluim, Remco Duits

We propose a framework for rotation and translation covariant deep learning using $SE(2)$ group convolutions.

no code implementations • 10 Mar 2016 • Erik J. Bekkers, Marco Loog, Bart M. ter Haar Romeny, Remco Duits

We propose a template matching method for the detection of 2D image objects that are characterized by orientation patterns.

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

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.