Vision

Publication

Distilling Internet-Scale Vision-Language Models into Embodied Agents

Kenneth Marino, Arun Ahuja, Rob Fergus, Ishita Dasgupta, Theodore Sumers *

arXiv

Download

Publication

Latent Space Smoothing for Individually Fair Representations

Momchil Peychev *, Anian Ruoss, Mislav Balunovic *, Maximilian Baader *, Martin Vechev *

ECCV

Download

Publication

Self-supervised video pretraining yields strong image representations

Nikhil Parthasarathy, Ali Eslami, Joao Carreira, Olivier Henaff

arXiv

Download

Publication

Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods

Skanda Koppula, Yazhe Li, Evan Shelhamer, Drew Jaegle, Nikhil Parthasarathy, Relja Arandjelovic, Joao Carreira, Olivier Henaff

NeurIPS Workshop

Download

Publication

Object discovery and representation networks

Olivier Henaff, Skanda Koppula, Evan Shelhamer, Daniel Zoran, Drew Jaegle, Andrew Zisserman, Joao Carreira, Relja Arandjelovic

ECCV

Download

Publication

Evaluating the Adversarial Robustness of Adaptive Test-time Defenses

Francesco Croce *, Sven Gowal, Thomas Brunner *, Evan Shelhamer, Matthias Hein *, Taylan Cemgil

ICML

Download

Publication

BYOL-Explore: Exploration with Bootstrapped Prediction

Zhaohan Daniel Guo, Shantanu Thakoor, Miruna Pîslar, Bernardo Avila Pires, Florent Altché, Corentin Tallec, Alaa Saade, Daniele Calandriello, Jean-Bastien Grill, Yunhao Tang, Michal Valko, Rémi Munos, Mohammad Gheshlaghi Azar, Bilal Piot

arXiv

Download

Publication

Unlocking High-Accuracy Differentially Private Image Classification through Scale

Soham De, Leonard Berrada, Jamie Hayes, Samuel L. Smith, Borja Balle

arXiv

Download

Publication

Perceiver AR: general-purpose, long-context autoregressive generation

Curtis Hawthorne, Andrew Jaegle, Cătălina Cangea, Sebastian Borgeaud, Charlie Nash, Mateusz Malinowski, Sander Dieleman, Oriol Vinyals, Matthew Botvinick, Ian Simon, Hannah Sheahan, Neil Zeghidour, Jean-Baptiste Alayrac, João Carreira, Jesse Engel

arXiv

Download

Publication

Measuring CLEVRness: Black-box Testing of Visual Reasoning Models

Spyridon Mouselinos *, Henryk Michalewski *, Mateusz Malinowski

ICLR

Download

Publication

More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech

Michael Hassid *, Michelle Tadmor Ramanovich *, Brendan Shillingford, Miaosen Wang, Ye Jia *, Tal Remez *

CVPR

Download

Publication

Efficient Visual Pretraining with Contrastive Detection

Olivier Henaff, Skanda Koppula, Jean-baptiste Alayrac, Aäron van den Oord, Oriol Vinyals, Joao Carreira

ICCV

Download

Publication

Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers

Antoine Miech, Jean-baptiste Alayrac, Ivan Laptev *, Josef Sivic *, Andrew Zisserman

CVPR

Download

Publication

Data, Architecture, or Losses: What Contributes Most to Multimodal Transformer Success?

Aida Nematzadeh, Lisa Anne Hendricks, Jean-baptiste Alayrac, Rosalia Schneider, John Mellor

Transactions of the Association for Computational Linguistics (TACL)

Download

Publication

BYOL works even without batch statistics

Pierre Richemond *, Jean-bastien Grill, Florent Altché, Corentin Tallec, Florian Strub, Andy Brock, Sam Smith, Soham De, Razvan Pascanu, Bilal Piot, Michal Valko

NeurIPS Workshop

Download

Publication

Bootstrap Your Own Latent: A new approach to self-supervised learning

Jean-bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Remi Munos, Michal Valko

NeurIPS

Download

Publication

S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency

Mel Vecerik, Jean-Baptist Regli, O Sushkov, D Barker, Rugile Pevcevciute, Thomas Rothörl, Christopher Schuster, Raia Hadsell, Lourdes Agapito *, Jonathan Scholz

arXiv

Download

Publication

Counting Out Time: Class Agnostic Video Repetition Counting in the Wild

Debidatta Dwibedi *, Yusuf Aytar, Jonathan Tompson *, Pierre Sermanet *, Andrew Zisserman

arXiv

Download

Publication

Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions

Ignacio Rocco *, Relja Arandjelović, Josef Sivic *

arXiv

Download

Publication

Evolving Normalization-Activation Layers

Hanxiao Liu *, Andrew Brock, Karen Simonyan, Quoc Le *

arXiv

Download

Publication

Hybrid Models for Open Set Recognition

H Zhang *, Ang Li, Jie Guo *, Y Guo *

arXiv

Download

Publication

Batch Normalization Biases Deep Residual Networks Towards Shallow Paths

Soham De, Samuel L. Smith

arXiv

Download

Publication

Sideways: Depth-Parallel Training of Video Models

Mateusz Malinowski, Grzegorz Swirszcz, Joao Carreira, Viorica Patraucean

arXiv

Download

Publication

International evaluation of an AI system for breast cancer screening

Scott Mayer McKinney *, Marcin T. Sieniek *, Varun Godbole *, Jonathan Godwin, Natasha Antropova, Hutan Ashrafian *, Trevor Back, Mary Chesus, Greg C Corrado *, Ara Darzi *, Mozziyar Etemadi *, Florencia Garcia-Vicente *, Fiona J Gilbert *, Mark Halling-Brown *, Demis Hassabis, Sunny Jansen *, Alan Karthikesalingam, Christopher J Kelly, Dominic King, Joseph Ledsam, David Melnick *, Hormuz Mostofi *, Bernardino Romera Paredes, Lily Peng *, Joshua Jay Reicher *, Richard Sidebottom *, Mustafa Suleyman, Daniel Tse *, Kenneth C. Young *, Jeffrey De Fauw, Shravya Shetty *

Nature

Download

Publication

End-to-End Learning of Visual Representations from Uncurated Instructional Videos

A Miech *, Jean-Baptiste Alayrac, Lucas Smaira, Ivan Laptev *, Josef Sivic *, Andrew Zisserman

arXiv

Download

Publications

Vision