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 Matthijs Douze

LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference


Apr 02, 2021
Ben Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jégou, Matthijs Douze


  Access Paper or Ask Questions

Training data-efficient image transformers & distillation through attention


Jan 15, 2021
Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, Hervé Jégou


  Access Paper or Ask Questions

Grafit: Learning fine-grained image representations with coarse labels


Nov 25, 2020
Hugo Touvron, Alexandre Sablayrolles, Matthijs Douze, Matthieu Cord, Hervé Jégou


  Access Paper or Ask Questions

Powers of layers for image-to-image translation


Aug 13, 2020
Hugo Touvron, Matthijs Douze, Matthieu Cord, Hervé Jégou


  Access Paper or Ask Questions

Generalized Many-Way Few-Shot Video Classification


Jul 09, 2020
Yongqin Xian, Bruno Korbar, Matthijs Douze, Bernt Schiele, Zeynep Akata, Lorenzo Torresani


  Access Paper or Ask Questions

Data Augmenting Contrastive Learning of Speech Representations in the Time Domain


Jul 02, 2020
Eugene Kharitonov, Morgane Rivière, Gabriel Synnaeve, Lior Wolf, Pierre-Emmanuel Mazaré, Matthijs Douze, Emmanuel Dupoux


  Access Paper or Ask Questions

Fixing the train-test resolution discrepancy: FixEfficientNet


Apr 20, 2020
Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Hervé Jégou


  Access Paper or Ask Questions

Radioactive data: tracing through training


Feb 03, 2020
Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Hervé Jégou


  Access Paper or Ask Questions

Lead2Gold: Towards exploiting the full potential of noisy transcriptions for speech recognition


Oct 16, 2019
Adrien Dufraux, Emmanuel Vincent, Awni Hannun, Armelle Brun, Matthijs Douze

* 8 pages, 4 tables, Accepted for publication in ASRU 2019 

  Access Paper or Ask Questions

White-box vs Black-box: Bayes Optimal Strategies for Membership Inference


Aug 29, 2019
Alexandre Sablayrolles, Matthijs Douze, Yann Ollivier, Cordelia Schmid, Hervé Jégou


  Access Paper or Ask Questions

Fixing the train-test resolution discrepancy


Jul 19, 2019
Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Hervé Jégou


  Access Paper or Ask Questions

MultiGrain: a unified image embedding for classes and instances


Apr 03, 2019
Maxim Berman, Hervé Jégou, Andrea Vedaldi, Iasonas Kokkinos, Matthijs Douze


  Access Paper or Ask Questions

Déjà Vu: an empirical evaluation of the memorization properties of ConvNets


Sep 17, 2018
Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Hervé Jégou


  Access Paper or Ask Questions

Deep Clustering for Unsupervised Learning of Visual Features


Jul 15, 2018
Mathilde Caron, Piotr Bojanowski, Armand Joulin, Matthijs Douze

* Accepted at ECCV 2018 

  Access Paper or Ask Questions

Low-shot learning with large-scale diffusion


Jun 15, 2018
Matthijs Douze, Arthur Szlam, Bharath Hariharan, Hervé Jégou


  Access Paper or Ask Questions

A neural network catalyzer for multi-dimensional similarity search


Jun 08, 2018
Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Hervé Jégou


  Access Paper or Ask Questions

Link and code: Fast indexing with graphs and compact regression codes


Apr 27, 2018
Matthijs Douze, Alexandre Sablayrolles, Hervé Jégou


  Access Paper or Ask Questions

How should we evaluate supervised hashing?


Aug 10, 2017
Alexandre Sablayrolles, Matthijs Douze, Hervé Jégou, Nicolas Usunier


  Access Paper or Ask Questions

An evaluation of large-scale methods for image instance and class discovery


Aug 09, 2017
Matthijs Douze, Hervé Jégou, Jeff Johnson

* Published at ACM Multimedia workshop 

  Access Paper or Ask Questions

Learning Joint Multilingual Sentence Representations with Neural Machine Translation


Aug 08, 2017
Holger Schwenk, Matthijs Douze

* 11 pages, 2 figures, published at ACL workshop RepL4NLP 

  Access Paper or Ask Questions

Billion-scale similarity search with GPUs


Feb 28, 2017
Jeff Johnson, Matthijs Douze, Hervé Jégou


  Access Paper or Ask Questions

FastText.zip: Compressing text classification models


Dec 12, 2016
Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Hérve Jégou, Tomas Mikolov

* Submitted to ICLR 2017 

  Access Paper or Ask Questions

Polysemous codes


Oct 10, 2016
Matthijs Douze, Hervé Jégou, Florent Perronnin

* The final (author) version of our ECCV'16 paper 

  Access Paper or Ask Questions

Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach


Mar 01, 2016
Mattis Paulin, Julien Mairal, Matthijs Douze, Zaid Harchaoui, Florent Perronnin, Cordelia Schmid


  Access Paper or Ask Questions