Search Results for author: Joni Dambre

Found 26 papers, 11 papers with code

Learned Thresholds Token Merging and Pruning for Vision Transformers

1 code implementation20 Jul 2023 Maxim Bonnaerens, Joni Dambre

Vision transformers have demonstrated remarkable success in a wide range of computer vision tasks over the last years.

Efficient ViTs

Towards the extraction of robust sign embeddings for low resource sign language recognition

no code implementations30 Jun 2023 Mathieu De Coster, Ellen Rushe, Ruth Holmes, Anthony Ventresque, Joni Dambre

However, due to a domain mismatch with their training sets and challenging poses in sign language, they lack robustness on sign language data and image-based models often still outperform keypoint-based models.

Imputation Sign Language Recognition +1

Hardware-aware mobile building block evaluation for computer vision

no code implementations26 Aug 2022 Maxim Bonnaerens, Matthias Freiberger, Marian Verhelst, Joni Dambre

In this work we propose a methodology to accurately evaluate and compare the performance of efficient neural network building blocks for computer vision in a hardware-aware manner.

Benchmarking Efficient Neural Network

Machine Translation from Signed to Spoken Languages: State of the Art and Challenges

no code implementations7 Feb 2022 Mathieu De Coster, Dimitar Shterionov, Mieke Van Herreweghe, Joni Dambre

Automatic translation from signed to spoken languages is an interdisciplinary research domain, lying on the intersection of computer vision, machine translation and linguistics.

Machine Translation Sign Language Translation +1

Frozen Pretrained Transformers for Neural Sign Language Translation

1 code implementation International Workshop on Automatic Translation for Signed and Spoken Languages (AT4SSL) 2021 Mathieu De Coster, Karel D'Oosterlinck, Marija Pizurica, Paloma Rabaey, Severine Verlinden, Mieke Van Herreweghe, Joni Dambre

Our results show that pretrained language models can be used to improve sign language translation performance and that the self-attention patterns in BERT transfer in zero-shot to the encoder and decoder of sign language translation models.

Decoder Machine Translation +3

Isolated Sign Recognition from RGB Video using Pose Flow and Self-Attention

1 code implementation Computer Vision and Pattern Recognition Workshops (CVPRW) 2021 Mathieu De Coster, Mieke Van Herreweghe, Joni Dambre

However, due to the limited amount of labeled data that is commonly available for training automatic sign (language) recognition, the VTN cannot reach its full potential in this domain.

Action Recognition Sign Language Recognition +1

Anchor Pruning for Object Detection

1 code implementation1 Apr 2021 Maxim Bonnaerens, Matthias Freiberger, Joni Dambre

In this work, we show that many anchors in the object detection head can be removed without any loss in accuracy.

Object object-detection +1

PyTorch-Hebbian: facilitating local learning in a deep learning framework

1 code implementation31 Jan 2021 Jules Talloen, Joni Dambre, Alexander Vandesompele

Using this framework, the potential of Hebbian learned feature extractors for image classification is illustrated.

Image Classification

Sign Language Recognition with Transformer Networks

no code implementations LREC 2020 Mathieu De Coster, Mieke Van Herreweghe, Joni Dambre

Sign language recognition can be used to speed up the annotation process of these corpora, in order to aid research into sign languages and sign language recognition.

Keypoint Estimation Sign Language Recognition

Populations of Spiking Neurons for Reservoir Computing: Closed Loop Control of a Compliant Quadruped

no code implementations9 Apr 2020 Alexander Vandesompele, Gabriel Urbain, Francis wyffels, Joni Dambre

Using the FORCE learning paradigm, we train a reservoir of spiking neuron populations to act as a central pattern generator.

Towards Deep Physical Reservoir Computing Through Automatic Task Decomposition And Mapping

no code implementations25 Oct 2019 Matthias Freiberger, Peter Bienstman, Joni Dambre

Photonic reservoir computing is a promising candidate for low-energy computing at high bandwidths.

Addressing Limited Weight Resolution in a Fully Optical Neuromorphic Reservoir Computing Readout

no code implementations6 Jun 2019 Chonghuai Ma, Floris Laporte, Joni Dambre, Peter Bienstman

Using optical hardware for neuromorphic computing has become more and more popular recently due to its efficient high-speed data processing capabilities and low power consumption.

Training Passive Photonic Reservoirs with Integrated Optical Readout

no code implementations8 Oct 2018 Matthias Freiberger, Andrew Katumba, Peter Bienstman, Joni Dambre

As Moore's law comes to an end, neuromorphic approaches to computing are on the rise.

Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules?

1 code implementation EMNLP 2018 Fréderic Godin, Kris Demuynck, Joni Dambre, Wesley De Neve, Thomas Demeester

In this paper, we investigate which character-level patterns neural networks learn and if those patterns coincide with manually-defined word segmentations and annotations.

Morphological Tagging

BRUNO: A Deep Recurrent Model for Exchangeable Data

3 code implementations NeurIPS 2018 Iryna Korshunova, Jonas Degrave, Ferenc Huszár, Yarin Gal, Arthur Gretton, Joni Dambre

We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations.

Anomaly Detection Bayesian Inference +2

Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks

2 code implementations25 Jul 2017 Fréderic Godin, Jonas Degrave, Joni Dambre, Wesley De Neve

A DReLU, which comes with an unbounded positive and negative image, can be used as a drop-in replacement for a tanh activation function in the recurrent step of Quasi-Recurrent Neural Networks (QRNNs) (Bradbury et al. (2017)).

Language Modelling Sentiment Analysis +1

Fast Face-swap Using Convolutional Neural Networks

no code implementations ICCV 2017 Iryna Korshunova, Wenzhe Shi, Joni Dambre, Lucas Theis

We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression, and lighting.

Face Swapping Style Transfer

A Differentiable Physics Engine for Deep Learning in Robotics

no code implementations5 Nov 2016 Jonas Degrave, Michiel Hermans, Joni Dambre, Francis wyffels

Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are omnipresent.

Evolutionary Algorithms Q-Learning

Rotation-invariant convolutional neural networks for galaxy morphology prediction

2 code implementations24 Mar 2015 Sander Dieleman, Kyle W. Willett, Joni Dambre

Unfortunately, even this approach does not scale well enough to keep up with the increasing availability of galaxy images.

General Classification Morphological Analysis +1

Photonic Delay Systems as Machine Learning Implementations

no code implementations12 Jan 2015 Michiel Hermans, Miguel Soriano, Joni Dambre, Peter Bienstman, Ingo Fischer

We perform physical experiments that demonstrate that the obtained input encodings work well in reality, and we show that optimized systems perform significantly better than the common Reservoir Computing approach.

BIG-bench Machine Learning

Trainable and Dynamic Computing: Error Backpropagation through Physical Media

no code implementations24 Jul 2014 Michiel Hermans, Michaël Burm, Joni Dambre, Peter Bienstman

Machine learning algorithms, and more in particular neural networks, arguably experience a revolution in terms of performance.

speech-recognition Speech Recognition

Memristor models for machine learning

no code implementations9 Jun 2014 Juan Pablo Carbajal, Joni Dambre, Michiel Hermans, Benjamin Schrauwen

In this work, we explore the use of memristor networks for analog approximate computation, based on a machine learning framework called reservoir computing.

BIG-bench Machine Learning

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