Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Sylvain Gelly

SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size


Apr 09, 2021
Jessica Yung, Rob Romijnders, Alexander Kolesnikov, Lucas Beyer, Josip Djolonga, Neil Houlsby, Sylvain Gelly, Mario Lucic, Xiaohua Zhai

* 4 pages (10 pages including references and appendix), 10 figures. Accepted at the ICLR 2021 RobustML Workshop. arXiv admin note: text overlap with arXiv:2007.08558 

  Access Paper or Ask Questions

Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark


Apr 06, 2021
Vincent Dumoulin, Neil Houlsby, Utku Evci, Xiaohua Zhai, Ross Goroshin, Sylvain Gelly, Hugo Larochelle


  Access Paper or Ask Questions

A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation


Oct 27, 2020
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem

* Journal of Machine Learning Research 2020, Volume 21, Number 209 
* arXiv admin note: substantial text overlap with arXiv:1811.12359 

  Access Paper or Ask Questions

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale


Oct 22, 2020
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby

* Fine-tuning code and pre-trained models are available at https://github.com/google-research/vision_transformer 

  Access Paper or Ask Questions

Scalable Transfer Learning with Expert Models


Sep 28, 2020
Joan Puigcerver, Carlos Riquelme, Basil Mustafa, Cedric Renggli, André Susano Pinto, Sylvain Gelly, Daniel Keysers, Neil Houlsby


  Access Paper or Ask Questions

A Commentary on the Unsupervised Learning of Disentangled Representations


Jul 28, 2020
Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem

* The Thirty-Fourth AAAI Conference on Artificial Intelligence 2020 (AAAI-20) 

  Access Paper or Ask Questions

What Do Neural Networks Learn When Trained With Random Labels?


Jun 18, 2020
Hartmut Maennel, Ibrahim Alabdulmohsin, Ilya Tolstikhin, Robert J. N. Baldock, Olivier Bousquet, Sylvain Gelly, Daniel Keysers


  Access Paper or Ask Questions

What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study


Jun 10, 2020
Marcin Andrychowicz, Anton Raichuk, Piotr Stańczyk, Manu Orsini, Sertan Girgin, Raphael Marinier, Léonard Hussenot, Matthieu Geist, Olivier Pietquin, Marcin Michalski, Sylvain Gelly, Olivier Bachem


  Access Paper or Ask Questions

Predicting Neural Network Accuracy from Weights


Feb 26, 2020
Thomas Unterthiner, Daniel Keysers, Sylvain Gelly, Olivier Bousquet, Ilya Tolstikhin


  Access Paper or Ask Questions

On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation


Jan 22, 2020
Nicolas Brosse, Carlos Riquelme, Alice Martin, Sylvain Gelly, Éric Moulines


  Access Paper or Ask Questions

Large Scale Learning of General Visual Representations for Transfer


Dec 24, 2019
Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby


  Access Paper or Ask Questions

Self-Supervised Learning of Video-Induced Visual Invariances


Dec 05, 2019
Michael Tschannen, Josip Djolonga, Marvin Ritter, Aravindh Mahendran, Neil Houlsby, Sylvain Gelly, Mario Lucic


  Access Paper or Ask Questions

Semantic Bottleneck Scene Generation


Nov 26, 2019
Samaneh Azadi, Michael Tschannen, Eric Tzeng, Sylvain Gelly, Trevor Darrell, Mario Lucic


  Access Paper or Ask Questions

The Visual Task Adaptation Benchmark


Oct 01, 2019
Xiaohua Zhai, Joan Puigcerver, Alexander Kolesnikov, Pierre Ruyssen, Carlos Riquelme, Mario Lucic, Josip Djolonga, Andre Susano Pinto, Maxim Neumann, Alexey Dosovitskiy, Lucas Beyer, Olivier Bachem, Michael Tschannen, Marcin Michalski, Olivier Bousquet, Sylvain Gelly, Neil Houlsby


  Access Paper or Ask Questions

On Mutual Information Maximization for Representation Learning


Jul 31, 2019
Michael Tschannen, Josip Djolonga, Paul K. Rubenstein, Sylvain Gelly, Mario Lucic

* Michael Tschannen and Josip Djolonga contributed equally 

  Access Paper or Ask Questions

Google Research Football: A Novel Reinforcement Learning Environment


Jul 25, 2019
Karol Kurach, Anton Raichuk, Piotr Stańczyk, Michał Zając, Olivier Bachem, Lasse Espeholt, Carlos Riquelme, Damien Vincent, Marcin Michalski, Olivier Bousquet, Sylvain Gelly


  Access Paper or Ask Questions

MULEX: Disentangling Exploitation from Exploration in Deep RL


Jul 01, 2019
Lucas Beyer, Damien Vincent, Olivier Teboul, Sylvain Gelly, Matthieu Geist, Olivier Pietquin


  Access Paper or Ask Questions

Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates


Jun 19, 2019
Hugo Penedones, Carlos Riquelme, Damien Vincent, Hartmut Maennel, Timothy Mann, Andre Barreto, Sylvain Gelly, Gergely Neu


  Access Paper or Ask Questions

When can unlabeled data improve the learning rate?


May 28, 2019
Christina Göpfert, Shai Ben-David, Olivier Bousquet, Sylvain Gelly, Ilya Tolstikhin, Ruth Urner


  Access Paper or Ask Questions

Evaluating Generative Models Using Divergence Frontiers


May 26, 2019
Josip Djolonga, Mario Lucic, Marco Cuturi, Olivier Bachem, Olivier Bousquet, Sylvain Gelly


  Access Paper or Ask Questions

High-Fidelity Image Generation With Fewer Labels


Mar 06, 2019
Mario Lucic, Michael Tschannen, Marvin Ritter, Xiaohua Zhai, Olivier Bachem, Sylvain Gelly

* Mario Lucic, Michael Tschannen, and Marvin Ritter contributed equally to this work 

  Access Paper or Ask Questions

Episodic Curiosity through Reachability


Feb 22, 2019
Nikolay Savinov, Anton Raichuk, Raphaël Marinier, Damien Vincent, Marc Pollefeys, Timothy Lillicrap, Sylvain Gelly

* Accepted to ICLR 2019. Code at https://github.com/google-research/episodic-curiosity/. Videos at https://sites.google.com/view/episodic-curiosity/ 

  Access Paper or Ask Questions

Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities


Feb 21, 2019
Octavian-Eugen Ganea, Sylvain Gelly, Gary Bécigneul, Aliaksei Severyn


  Access Paper or Ask Questions

Parameter-Efficient Transfer Learning for NLP


Feb 02, 2019
Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, Sylvain Gelly


  Access Paper or Ask Questions

Towards Accurate Generative Models of Video: A New Metric & Challenges


Dec 03, 2018
Thomas Unterthiner, Sjoerd van Steenkiste, Karol Kurach, Raphael Marinier, Marcin Michalski, Sylvain Gelly


  Access Paper or Ask Questions

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations


Dec 02, 2018
Francesco Locatello, Stefan Bauer, Mario Lucic, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem

* This is a preliminary preprint based on our initial experimental results 

  Access Paper or Ask Questions

Are GANs Created Equal? A Large-Scale Study


Oct 29, 2018
Mario Lucic, Karol Kurach, Marcin Michalski, Sylvain Gelly, Olivier Bousquet

* NIPS'18: Added a section on the limitations of the study and additional empirical results 

  Access Paper or Ask Questions

Assessing Generative Models via Precision and Recall


Oct 28, 2018
Mehdi S. M. Sajjadi, Olivier Bachem, Mario Lucic, Olivier Bousquet, Sylvain Gelly

* NIPS 2018 

  Access Paper or Ask Questions

The GAN Landscape: Losses, Architectures, Regularization, and Normalization


Oct 26, 2018
Karol Kurach, Mario Lucic, Xiaohua Zhai, Marcin Michalski, Sylvain Gelly

* Changed formatting from ICML workshop to ICLR. We added additional resnet ablation studies, hinge loss, and an empirical comparison between KID and FID 

  Access Paper or Ask Questions

A Case for Object Compositionality in Deep Generative Models of Images


Oct 17, 2018
Sjoerd van Steenkiste, Karol Kurach, Sylvain Gelly


  Access Paper or Ask Questions