Search Results for author: Hervé Jégou

Found 43 papers, 30 papers with code

DeiT III: Revenge of the ViT

2 code implementations14 Apr 2022 Hugo Touvron, Matthieu Cord, Hervé Jégou

Our evaluations on Image classification (ImageNet-1k with and without pre-training on ImageNet-21k), transfer learning and semantic segmentation show that our procedure outperforms by a large margin previous fully supervised training recipes for ViT.

 Ranked #1 on Image Classification on ImageNet ReaL (Number of params metric)

Data Augmentation Image Classification +3

Three things everyone should know about Vision Transformers

4 code implementations18 Mar 2022 Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby, Jakob Verbeek, Hervé Jégou

(2) Fine-tuning the weights of the attention layers is sufficient to adapt vision transformers to a higher resolution and to other classification tasks.

Ranked #6 on Image Classification on CIFAR-10 (using extra training data)

Fine-Grained Image Classification Natural Language Processing

Watermarking Images in Self-Supervised Latent Spaces

1 code implementation17 Dec 2021 Pierre Fernandez, Alexandre Sablayrolles, Teddy Furon, Hervé Jégou, Matthijs Douze

We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches.

Data Augmentation

Nearest neighbor search with compact codes: A decoder perspective

no code implementations17 Dec 2021 Kenza Amara, Matthijs Douze, Alexandre Sablayrolles, Hervé Jégou

Modern approaches for fast retrieval of similar vectors on billion-scaled datasets rely on compressed-domain approaches such as binary sketches or product quantization.


ResNet strikes back: An improved training procedure in timm

8 code implementations NeurIPS Workshop ImageNet_PPF 2021 Ross Wightman, Hugo Touvron, Hervé Jégou

We share competitive training settings and pre-trained models in the timm open-source library, with the hope that they will serve as better baselines for future work.

Data Augmentation Fine-Grained Image Classification

Emerging Properties in Self-Supervised Vision Transformers

16 code implementations ICCV 2021 Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, Julien Mairal, Piotr Bojanowski, Armand Joulin

In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets).

Copy Detection Self-Supervised Image Classification +5

Going deeper with Image Transformers

14 code implementations ICCV 2021 Hugo Touvron, Matthieu Cord, Alexandre Sablayrolles, Gabriel Synnaeve, Hervé Jégou

In particular, we investigate the interplay of architecture and optimization of such dedicated transformers.

 Ranked #1 on on

Image Classification Transfer Learning

Training Vision Transformers for Image Retrieval

no code implementations10 Feb 2021 Alaaeldin El-Nouby, Natalia Neverova, Ivan Laptev, Hervé Jégou

Transformers have shown outstanding results for natural language understanding and, more recently, for image classification.

Image Classification Image Retrieval +2

Powers of layers for image-to-image translation

no code implementations13 Aug 2020 Hugo Touvron, Matthijs Douze, Matthieu Cord, Hervé Jégou

We propose a simple architecture to address unpaired image-to-image translation tasks: style or class transfer, denoising, deblurring, deblocking, etc.

 Ranked #1 on Image-to-Image Translation on horse2zebra (Frechet Inception Distance metric)

Deblurring Denoising +2

Fixing the train-test resolution discrepancy: FixEfficientNet

1 code implementation18 Mar 2020 Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Hervé Jégou

An EfficientNet-L2 pre-trained with weak supervision on 300M unlabeled images and further optimized with FixRes achieves 88. 5% top-1 accuracy (top-5: 98. 7%), which establishes the new state of the art for ImageNet with a single crop.

Ranked #8 on Image Classification on ImageNet ReaL (using extra training data)

Data Augmentation Image Classification

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

no code implementations29 Aug 2019 Alexandre Sablayrolles, Matthijs Douze, Yann Ollivier, Cordelia Schmid, Hervé Jégou

Membership inference determines, given a sample and trained parameters of a machine learning model, whether the sample was part of the training set.

Large Memory Layers with Product Keys

7 code implementations NeurIPS 2019 Guillaume Lample, Alexandre Sablayrolles, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou

In our experiments we consider a dataset with up to 30 billion words, and we plug our memory layer in a state-of-the-art transformer-based architecture.

Language Modelling

Fixing the train-test resolution discrepancy

3 code implementations NeurIPS 2019 Hugo Touvron, Andrea Vedaldi, Matthijs Douze, Hervé Jégou

Conversely, when training a ResNeXt-101 32x48d pre-trained in weakly-supervised fashion on 940 million public images at resolution 224x224 and further optimizing for test resolution 320x320, we obtain a test top-1 accuracy of 86. 4% (top-5: 98. 0%) (single-crop).

Ranked #2 on Fine-Grained Image Classification on Birdsnap (using extra training data)

Data Augmentation Fine-Grained Image Classification +1

Understanding and Improving Kernel Local Descriptors

3 code implementations27 Nov 2018 Arun Mukundan, Giorgos Tolias, Andrei Bursuc, Hervé Jégou, Ondřej Chum

We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients.

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

no code implementations ICLR 2019 Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Hervé Jégou

Convolutional neural networks memorize part of their training data, which is why strategies such as data augmentation and drop-out are employed to mitigate overfitting.

Data Augmentation

Spreading vectors for similarity search

1 code implementation ICLR 2019 Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid, Hervé Jégou

Discretizing multi-dimensional data distributions is a fundamental step of modern indexing methods.


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

5 code implementations CVPR 2018 Matthijs Douze, Alexandre Sablayrolles, Hervé Jégou

Similarity search approaches based on graph walks have recently attained outstanding speed-accuracy trade-offs, taking aside the memory requirements.

Image Similarity Search Quantization

Word Translation Without Parallel Data

17 code implementations ICLR 2018 Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou

We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine translation.

Cross-Lingual Word Embeddings Translation +4

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

no code implementations9 Aug 2017 Matthijs Douze, Hervé Jégou, Jeff Johnson

While k-means is usually considered as the gold standard for this task, we evaluate and show the interest of diffusion methods that have been neglected by the state of the art, such as the Markov Clustering algorithm.

Instance Search

Low-shot learning with large-scale diffusion

1 code implementation CVPR 2018 Matthijs Douze, Arthur Szlam, Bharath Hariharan, Hervé Jégou

This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time.

graph construction

Billion-scale similarity search with GPUs

11 code implementations28 Feb 2017 Jeff Johnson, Matthijs Douze, Hervé Jégou

Similarity search finds application in specialized database systems handling complex data such as images or videos, which are typically represented by high-dimensional features and require specific indexing structures.

Image Similarity Search Quantization

Interferences in match kernels

no code implementations24 Nov 2016 Naila Murray, Hervé Jégou, Florent Perronnin, Andrew Zisserman

The second one involves equalising the match of a single descriptor to the aggregated vector.

Image Retrieval

How should we evaluate supervised hashing?

1 code implementation21 Sep 2016 Alexandre Sablayrolles, Matthijs Douze, Hervé Jégou, Nicolas Usunier

Hashing produces compact representations for documents, to perform tasks like classification or retrieval based on these short codes.

General Classification Transfer Learning

Efficient softmax approximation for GPUs

12 code implementations ICML 2017 Edouard Grave, Armand Joulin, Moustapha Cissé, David Grangier, Hervé Jégou

We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies.

Polysemous codes

8 code implementations7 Sep 2016 Matthijs Douze, Hervé Jégou, Florent Perronnin

This paper considers the problem of approximate nearest neighbor search in the compressed domain.


Approximate search with quantized sparse representations

no code implementations10 Aug 2016 Himalaya Jain, Patrick Pérez, Rémi Gribonval, Joaquin Zepeda, Hervé Jégou

This paper tackles the task of storing a large collection of vectors, such as visual descriptors, and of searching in it.


Tubelets: Unsupervised action proposals from spatiotemporal super-voxels

no code implementations7 Jul 2016 Mihir Jain, Jan van Gemert, Hervé Jégou, Patrick Bouthemy, Cees G. M. Snoek

First, inspired by selective search for object proposals, we introduce an approach to generate action proposals from spatiotemporal super-voxels in an unsupervised manner, we call them Tubelets.

Action Localization

Particular object retrieval with integral max-pooling of CNN activations

6 code implementations18 Nov 2015 Giorgos Tolias, Ronan Sicre, Hervé Jégou

Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations.

Image Retrieval Re-Ranking

Memory vectors for similarity search in high-dimensional spaces

no code implementations10 Dec 2014 Ahmet Iscen, Teddy Furon, Vincent Gripon, Michael Rabbat, Hervé Jégou

We study an indexing architecture to store and search in a database of high-dimensional vectors from the perspective of statistical signal processing and decision theory.

Image Retrieval

A comparison of dense region detectors for image search and fine-grained classification

no code implementations29 Oct 2014 Ahmet Iscen, Giorgos Tolias, Philippe-Henri Gosselin, Hervé Jégou

Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks.

General Classification Image Classification +1

Orientation covariant aggregation of local descriptors with embeddings

no code implementations8 Jul 2014 Giorgos Tolias, Teddy Furon, Hervé Jégou

Our geometric-aware aggregation strategy is effective for image search, as shown by experiments performed on standard benchmarks for image and particular object retrieval, namely Holidays and Oxford buildings.

Image Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.