no code implementations • ICLR 2019 • Alex Mott, Daniel Zoran, Mike Chrzanowski, Daan Wierstra, Danilo J. Rezende
We present a soft, spatial, sequential, top-down attention model (S3TA).
no code implementations • 1 Dec 2023 • João Carreira, Michael King, Viorica Pătrăucean, Dilara Gokay, Cătălin Ionescu, Yi Yang, Daniel Zoran, Joseph Heyward, Carl Doersch, Yusuf Aytar, Dima Damen, Andrew Zisserman
We introduce a framework for online learning from a single continuous video stream -- the way people and animals learn, without mini-batches, data augmentation or shuffling.
1 code implementation • 29 Nov 2023 • Drew A. Hudson, Daniel Zoran, Mateusz Malinowski, Andrew K. Lampinen, Andrew Jaegle, James L. McClelland, Loic Matthey, Felix Hill, Alexander Lerchner
We introduce SODA, a self-supervised diffusion model, designed for representation learning.
no code implementations • 13 Jan 2023 • Pol Moreno, Adam R. Kosiorek, Heiko Strathmann, Daniel Zoran, Rosalia G. Schneider, Björn Winckler, Larisa Markeeva, Théophane Weber, Danilo J. Rezende
NeRF provides unparalleled fidelity of novel view synthesis: rendering a 3D scene from an arbitrary viewpoint.
no code implementations • 20 Oct 2022 • Ryan Faulkner, Daniel Zoran
The ability to carve the world into useful abstractions in order to reason about time and space is a crucial component of intelligence.
1 code implementation • 16 Mar 2022 • Olivier J. Hénaff, Skanda Koppula, Evan Shelhamer, Daniel Zoran, Andrew Jaegle, Andrew Zisserman, João Carreira, Relja Arandjelović
The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks.
2 code implementations • 22 Feb 2022 • Joao Carreira, Skanda Koppula, Daniel Zoran, Adria Recasens, Catalin Ionescu, Olivier Henaff, Evan Shelhamer, Relja Arandjelovic, Matt Botvinick, Oriol Vinyals, Karen Simonyan, Andrew Zisserman, Andrew Jaegle
This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video.
7 code implementations • ICLR 2022 • Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Daniel Zoran, Andrew Brock, Evan Shelhamer, Olivier Hénaff, Matthew M. Botvinick, Andrew Zisserman, Oriol Vinyals, Joāo Carreira
A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible.
Ranked #1 on Optical Flow Estimation on KITTI 2015 (Average End-Point Error metric)
1 code implementation • NeurIPS 2021 • Rishabh Kabra, Daniel Zoran, Goker Erdogan, Loic Matthey, Antonia Creswell, Matthew Botvinick, Alexander Lerchner, Christopher P. Burgess
Leveraging the shared structure that exists across different scenes, our model learns to infer two sets of latent representations from RGB video input alone: a set of "object" latents, corresponding to the time-invariant, object-level contents of the scene, as well as a set of "frame" latents, corresponding to global time-varying elements such as viewpoint.
1 code implementation • 1 Apr 2021 • Adam R. Kosiorek, Heiko Strathmann, Daniel Zoran, Pol Moreno, Rosalia Schneider, Soňa Mokrá, Danilo J. Rezende
We propose NeRF-VAE, a 3D scene generative model that incorporates geometric structure via NeRF and differentiable volume rendering.
no code implementations • ICCV 2021 • Daniel Zoran, Rishabh Kabra, Alexander Lerchner, Danilo J. Rezende
We present a model that is able to segment visual scenes from complex 3D environments into distinct objects, learn disentangled representations of individual objects, and form consistent and coherent predictions of future frames, in a fully unsupervised manner.
no code implementations • CVPR 2020 • Daniel Zoran, Mike Chrzanowski, Po-Sen Huang, Sven Gowal, Alex Mott, Pushmeet Kohl
In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception.
1 code implementation • NeurIPS 2019 • Alex Mott, Daniel Zoran, Mike Chrzanowski, Daan Wierstra, Danilo J. Rezende
Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain.
6 code implementations • 1 Mar 2019 • Klaus Greff, Raphaël Lopez Kaufman, Rishabh Kabra, Nick Watters, Chris Burgess, Daniel Zoran, Loic Matthey, Matthew Botvinick, Alexander Lerchner
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities.
no code implementations • ICLR 2019 • Avraham Ruderman, Neil C. Rabinowitz, Ari S. Morcos, Daniel Zoran
In this work, we rigorously test these questions, and find that deformation stability in convolutional networks is more nuanced than it first appears: (1) Deformation invariance is not a binary property, but rather that different tasks require different degrees of deformation stability at different layers.
1 code implementation • 24 Jan 2018 • Joel Z. Leibo, Cyprien de Masson d'Autume, Daniel Zoran, David Amos, Charles Beattie, Keith Anderson, Antonio García Castañeda, Manuel Sanchez, Simon Green, Audrunas Gruslys, Shane Legg, Demis Hassabis, Matthew M. Botvinick
Psychlab is a simulated psychology laboratory inside the first-person 3D game world of DeepMind Lab (Beattie et al. 2016).
1 code implementation • ICML 2018 • Danny Karmon, Daniel Zoran, Yoav Goldberg
Most works on adversarial examples for deep-learning based image classifiers use noise that, while small, covers the entire image.
no code implementations • NeurIPS 2017 • Nicholas Watters, Daniel Zoran, Theophane Weber, Peter Battaglia, Razvan Pascanu, Andrea Tacchetti
We introduce the Visual Interaction Network, a general-purpose model for learning the dynamics of a physical system from raw visual observations.
1 code implementation • NeurIPS 2017 • Jörg Bornschein, andriy mnih, Daniel Zoran, Danilo J. Rezende
Aiming to augment generative models with external memory, we interpret the output of a memory module with stochastic addressing as a conditional mixture distribution, where a read operation corresponds to sampling a discrete memory address and retrieving the corresponding content from memory.
3 code implementations • 5 Jun 2017 • Nicholas Watters, Andrea Tacchetti, Theophane Weber, Razvan Pascanu, Peter Battaglia, Daniel Zoran
We found that from just six input video frames the Visual Interaction Network can generate accurate future trajectories of hundreds of time steps on a wide range of physical systems.
1 code implementation • 28 Feb 2017 • Daniel Zoran, Balaji Lakshminarayanan, Charles Blundell
We introduce a new method called differentiable boundary tree which allows for learning deep kNN representations.
no code implementations • CVPR 2016 • Katherine L. Bouman, Michael D. Johnson, Daniel Zoran, Vincent L. Fish, Sheperd S. Doeleman, William T. Freeman
Very long baseline interferometry (VLBI) is a technique for imaging celestial radio emissions by simultaneously observing a source from telescopes distributed across Earth.
no code implementations • ICCV 2015 • Daniel Zoran, Phillip Isola, Dilip Krishnan, William T. Freeman
We demonstrate that this frame- work works well on two important mid-level vision tasks: intrinsic image decomposition and depth from an RGB im- age.
2 code implementations • 21 Nov 2015 • Phillip Isola, Daniel Zoran, Dilip Krishnan, Edward H. Adelson
We propose a self-supervised framework that learns to group visual entities based on their rate of co-occurrence in space and time.
no code implementations • NeurIPS 2014 • Daniel Zoran, Dilip Krishnan, José Bento, Bill Freeman
The Generic Viewpoint Assumption (GVA) states that the position of the viewer or the light in a scene is not special.
no code implementations • NeurIPS 2013 • Dan Rosenbaum, Daniel Zoran, Yair Weiss
Motivated by recent progress in natural image statistics, we use newly available datasets with ground truth optical flow to learn the local statistics of optical flow and rigorously compare the learned model to prior models assumed by computer vision optical flow algorithms.
no code implementations • NeurIPS 2012 • Daniel Zoran, Yair Weiss
Simple Gaussian Mixture Models (GMMs) learned from pixels of natural image patches have been recently shown to be surprisingly strong performers in modeling the statistics of natural images.
no code implementations • NeurIPS 2009 • Daniel Zoran, Yair Weiss
We propose a new model for natural image statistics.