Timezone: »
Subsampling is used in convolutional neural networks (CNNs) in the form of pooling or strided convolutions, to reduce the spatial dimensions of feature maps and to allow the receptive fields to grow exponentially with depth. However, it is known that such subsampling operations are not translation equivariant, unlike convolutions that are translation equivariant. Here, we first introduce translation equivariant subsampling/upsampling layers that can be used to construct exact translation equivariant CNNs. We then generalise these layers beyond translations to general groups, thus proposing group equivariant subsampling/upsampling. We use these layers to construct group equivariant autoencoders (GAEs) that allow us to learn low-dimensional equivariant representations. We empirically verify on images that the representations are indeed equivariant to input translations and rotations, and thus generalise well to unseen positions and orientations. We further use GAEs in models that learn object-centric representations on multi-object datasets, and show improved data efficiency and decomposition compared to non-equivariant baselines.
Author Information
Jin Xu (University of Oxford)
Hyunjik Kim (DeepMind)
Thomas Rainforth (University of Oxford)
Yee Teh (DeepMind)
More from the Same Authors
-
2021 : Certifiably Robust Variational Autoencoders »
Ben Barrett · Alexander Camuto · Matthew Willetts · Thomas Rainforth -
2021 : Certifiably Robust Variational Autoencoders »
Ben Barrett · Alexander Camuto · Matthew Willetts · Thomas Rainforth -
2021 : Uncertainty Quantification in End-to-End Implicit Neural Representations for Medical Imaging »
Francisca Vasconcelos · Bobby He · Yee Teh -
2021 : Certifiably Robust Variational Autoencoders »
Ben Barrett · Alexander Camuto · Matthew Willetts · Thomas Rainforth -
2023 Poster: Trans-Dimensional Generative Modeling via Jump Diffusion Models »
Andrew Campbell · William Harvey · Christian Weilbach · Valentin De Bortoli · Thomas Rainforth · Arnaud Doucet -
2023 Poster: Deep Stochastic Processes via Functional Markov Transition Operators »
Jin Xu · Emilien Dupont · Kaspar Märtens · Thomas Rainforth · Yee Whye Teh -
2022 Poster: A Continuous Time Framework for Discrete Denoising Models »
Andrew Campbell · Joe Benton · Valentin De Bortoli · Thomas Rainforth · George Deligiannidis · Arnaud Doucet -
2022 Poster: Rethinking Variational Inference for Probabilistic Programs with Stochastic Support »
Tim Reichelt · Luke Ong · Thomas Rainforth -
2022 Poster: Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation »
Jannik Kossen · Sebastian Farquhar · Yarin Gal · Thomas Rainforth -
2021 Poster: On Contrastive Representations of Stochastic Processes »
Emile Mathieu · Adam Foster · Yee Teh -
2021 Poster: Powerpropagation: A sparsity inducing weight reparameterisation »
Jonathan Richard Schwarz · Siddhant Jayakumar · Razvan Pascanu · Peter E Latham · Yee Teh -
2021 Poster: Implicit Deep Adaptive Design: Policy-Based Experimental Design without Likelihoods »
Desi R Ivanova · Adam Foster · Steven Kleinegesse · Michael Gutmann · Thomas Rainforth -
2021 Poster: Online Variational Filtering and Parameter Learning »
Andrew Campbell · Yuyang Shi · Thomas Rainforth · Arnaud Doucet -
2021 Poster: On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations »
Tim G. J. Rudner · Cong Lu · Michael A Osborne · Yarin Gal · Yee Teh -
2021 Poster: Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels »
Michael Hutchinson · Alexander Terenin · Viacheslav Borovitskiy · So Takao · Yee Teh · Marc Deisenroth -
2021 Poster: BayesIMP: Uncertainty Quantification for Causal Data Fusion »
Siu Lun Chau · Jean-Francois Ton · Javier González · Yee Teh · Dino Sejdinovic -
2021 Poster: Neural Ensemble Search for Uncertainty Estimation and Dataset Shift »
Sheheryar Zaidi · Arber Zela · Thomas Elsken · Chris C Holmes · Frank Hutter · Yee Teh -
2021 Poster: Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning »
Jannik Kossen · Neil Band · Clare Lyle · Aidan Gomez · Thomas Rainforth · Yarin Gal -
2021 Oral: Online Variational Filtering and Parameter Learning »
Andrew Campbell · Yuyang Shi · Thomas Rainforth · Arnaud Doucet -
2019 Poster: On the Fairness of Disentangled Representations »
Francesco Locatello · Gabriele Abbati · Thomas Rainforth · Stefan Bauer · Bernhard Schölkopf · Olivier Bachem -
2019 Poster: Variational Bayesian Optimal Experimental Design »
Adam Foster · Martin Jankowiak · Elias Bingham · Paul Horsfall · Yee Whye Teh · Thomas Rainforth · Noah Goodman -
2019 Spotlight: Variational Bayesian Optimal Experimental Design »
Adam Foster · Martin Jankowiak · Elias Bingham · Paul Horsfall · Yee Whye Teh · Thomas Rainforth · Noah Goodman -
2018 : Panel on research process »
Zachary Lipton · Charles Sutton · Finale Doshi-Velez · Hanna Wallach · Suchi Saria · Rich Caruana · Thomas Rainforth -
2018 : Introduction of the workshop »
Razvan Pascanu · Yee Teh · Mark Ring · Marc Pickett -
2018 Workshop: Continual Learning »
Razvan Pascanu · Yee Teh · Marc Pickett · Mark Ring -
2018 Workshop: Critiquing and Correcting Trends in Machine Learning »
Thomas Rainforth · Matt Kusner · Benjamin Bloem-Reddy · Brooks Paige · Rich Caruana · Yee Whye Teh -
2018 Poster: Faithful Inversion of Generative Models for Effective Amortized Inference »
Stefan Webb · Adam Golinski · Rob Zinkov · Siddharth N · Thomas Rainforth · Yee Whye Teh · Frank Wood -
2018 Poster: Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects »
Adam Kosiorek · Hyunjik Kim · Yee Whye Teh · Ingmar Posner -
2018 Spotlight: Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects »
Adam Kosiorek · Hyunjik Kim · Yee Whye Teh · Ingmar Posner -
2017 : Poster Spotlights »
Francesco Locatello · Ari Pakman · Da Tang · Thomas Rainforth · Zalan Borsos · Marko Järvenpää · Eric Nalisnick · Gabriele Abbati · XIAOYU LU · Jonathan Huggins · Rachit Singh · Rui Luo -
2017 Poster: Distral: Robust multitask reinforcement learning »
Yee Teh · Victor Bapst · Wojciech Czarnecki · John Quan · James Kirkpatrick · Raia Hadsell · Nicolas Heess · Razvan Pascanu -
2017 Poster: Filtering Variational Objectives »
Chris Maddison · John Lawson · George Tucker · Nicolas Heess · Mohammad Norouzi · Andriy Mnih · Arnaud Doucet · Yee Teh -
2016 : Probabilistic structure discovery in time series data »
David Janz · Brooks Paige · Thomas Rainforth · Jan-Willem van de Meent -
2016 Poster: Bayesian Optimization for Probabilistic Programs »
Thomas Rainforth · Tuan Anh Le · Jan-Willem van de Meent · Michael A Osborne · Frank Wood