Search Results for author: Jakob Verbeek

Found 38 papers, 17 papers with code

Three things everyone should know about Vision Transformers

3 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 #4 on Image Classification on CIFAR-10 (using extra training data)

Fine-Grained Image Classification

FlexIT: Towards Flexible Semantic Image Translation

no code implementations9 Mar 2022 Guillaume Couairon, Asya Grechka, Jakob Verbeek, Holger Schwenk, Matthieu Cord

Via the latent space of an auto-encoder, we iteratively transform the input image toward the target point, ensuring coherence and quality with a variety of novel regularization terms.

Image Generation Translation

XCiT: Cross-Covariance Image Transformers

10 code implementations NeurIPS 2021 Alaaeldin El-Nouby, Hugo Touvron, Mathilde Caron, Piotr Bojanowski, Matthijs Douze, Armand Joulin, Ivan Laptev, Natalia Neverova, Gabriel Synnaeve, Jakob Verbeek, Hervé Jegou

We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries.

Instance Segmentation Object Detection +2

Dual Mesh Convolutional Networks for Human Shape Correspondence

no code implementations23 Mar 2021 Nitika Verma, Adnane Boukhayma, Jakob Verbeek, Edmond Boyer

Convolutional networks have been extremely successful for regular data structures such as 2D images and 3D voxel grids.

3D Shape Representation

Meta-Learning with Shared Amortized Variational Inference

1 code implementation ICML 2020 Ekaterina Iakovleva, Jakob Verbeek, Karteek Alahari

We propose a novel amortized variational inference scheme for an empirical Bayes meta-learning model, where model parameters are treated as latent variables.

Meta-Learning Variational Inference

Efficient Wait-k Models for Simultaneous Machine Translation

1 code implementation18 May 2020 Maha Elbayad, Laurent Besacier, Jakob Verbeek

We also show that the 2D-convolution architecture is competitive with Transformers for simultaneous translation of spoken language.

Machine Translation Translation

Anytime Inference with Distilled Hierarchical Neural Ensembles

1 code implementation3 Mar 2020 Adria Ruiz, Jakob Verbeek

We propose Hierarchical Neural Ensembles (HNE), a novel framework to embed an ensemble of multiple networks in a hierarchical tree structure, sharing intermediate layers.

Image Classification

Improved Training Techniques for Online Neural Machine Translation

no code implementations25 Sep 2019 Maha Elbayad, Laurent Besacier, Jakob Verbeek

We investigate the sensitivity of such models to the value of k that is used during training and when deploying the model, and the effect of updating the hidden states in transformer models as new source tokens are read.

Automatic Speech Recognition Machine Translation +1

Hierarchical Scene Coordinate Classification and Regression for Visual Localization

no code implementations CVPR 2020 Xiaotian Li, Shuzhe Wang, Yi Zhao, Jakob Verbeek, Juho Kannala

In this work, we present a new hierarchical scene coordinate network to predict pixel scene coordinates in a coarse-to-fine manner from a single RGB image.

Classification Data Augmentation +2

Probabilistic Reconstruction Networks for 3D Shape Inference from a Single Image

1 code implementation20 Aug 2019 Roman Klokov, Jakob Verbeek, Edmond Boyer

We study end-to-end learning strategies for 3D shape inference from images, in particular from a single image.

3D Reconstruction

Adaptative Inference Cost With Convolutional Neural Mixture Models

no code implementations ICCV 2019 Adria Ruiz, Jakob Verbeek

Despite the outstanding performance of convolutional neural networks (CNNs) for many vision tasks, the required computational cost during inference is problematic when resources are limited.

Image Classification Semantic Segmentation

Reference-based Variational Autoencoders

no code implementations ICLR Workshop LLD 2019 Adrià Ruiz, Oriol Martinez, Xavier Binefa, Jakob Verbeek

Given a pool of unlabelled images, the goal is to learn a representation where a set of target factors are disentangled from others.

Conditional Image Generation

Learning Disentangled Representations with Reference-Based Variational Autoencoders

no code implementations24 Jan 2019 Adria Ruiz, Oriol Martinez, Xavier Binefa, Jakob Verbeek

Given a pool of unlabeled images, the goal is to learn a representation where a set of target factors are disentangled from others.

Conditional Image Generation

Adaptive Density Estimation for Generative Models

no code implementations NeurIPS 2019 Thomas Lucas, Konstantin Shmelkov, Karteek Alahari, Cordelia Schmid, Jakob Verbeek

We show that our model significantly improves over existing hybrid models: offering GAN-like samples, IS and FID scores that are competitive with fully adversarial models, and improved likelihood scores.

Density Estimation

Understanding Priors in Bayesian Neural Networks at the Unit Level

no code implementations11 Oct 2018 Mariia Vladimirova, Jakob Verbeek, Pablo Mesejo, Julyan Arbel

We investigate deep Bayesian neural networks with Gaussian weight priors and a class of ReLU-like nonlinearities.

Coverage and Quality Driven Training of Generative Image Models

no code implementations27 Sep 2018 Thomas Lucas, Konstantin Shmelkov, Karteek Alahari, Cordelia Schmid, Jakob Verbeek

First, we propose a model that extends variational autoencoders by using deterministic invertible transformation layers to map samples from the decoder to the image space.

Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction

3 code implementations CONLL 2018 Maha Elbayad, Laurent Besacier, Jakob Verbeek

Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding.

Machine Translation Translation

Mixed batches and symmetric discriminators for GAN training

no code implementations ICML 2018 Thomas Lucas, Corentin Tallec, Jakob Verbeek, Yann Ollivier

We propose to feed the discriminator with mixed batches of true and fake samples, and train it to predict the ratio of true samples in the batch.

Token-level and sequence-level loss smoothing for RNN language models

1 code implementation ACL 2018 Maha Elbayad, Laurent Besacier, Jakob Verbeek

We extend this approach to token-level loss smoothing, and propose improvements to the sequence-level smoothing approach.

Image Captioning Machine Translation +1

Auxiliary Guided Autoregressive Variational Autoencoders

no code implementations ICLR 2018 Thomas Lucas, Jakob Verbeek

Our contribution is a training procedure relying on an auxiliary loss function that controls which information is captured by the latent variables and what is left to the autoregressive decoder.

FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis

1 code implementation CVPR 2018 Nitika Verma, Edmond Boyer, Jakob Verbeek

Convolutional neural networks (CNNs) have massively impacted visual recognition in 2D images, and are now ubiquitous in state-of-the-art approaches.

Semantic Segmentation using Adversarial Networks

1 code implementation25 Nov 2016 Pauline Luc, Camille Couprie, Soumith Chintala, Jakob Verbeek

Adversarial training has been shown to produce state of the art results for generative image modeling.

Semantic Segmentation

Convolutional Neural Fabrics

no code implementations NeurIPS 2016 Shreyas Saxena, Jakob Verbeek

Despite the success of CNNs, selecting the optimal architecture for a given task remains an open problem.

Image Classification Semantic Segmentation

Approximate Fisher Kernels of non-iid Image Models for Image Categorization

no code implementations3 Oct 2015 Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid

It has been experimentally observed that the performance of BoW and FV representations can be improved by employing discounting transformations such as power normalization.

Image Categorization

Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning

no code implementations3 Mar 2015 Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid

In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations.

Multiple Instance Learning Weakly-Supervised Object Localization

Efficient Action Localization with Approximately Normalized Fisher Vectors

no code implementations CVPR 2014 Dan Oneata, Jakob Verbeek, Cordelia Schmid

Transformation of the FV by power and L2 normalizations has shown to significantly improve its performance, and led to state-of-the-art results for a range of image and video classification and retrieval tasks.

Action Recognition General Classification +1

Multi-fold MIL Training for Weakly Supervised Object Localization

no code implementations CVPR 2014 Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid

In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations.

Multiple Instance Learning Weakly-Supervised Object Localization

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