Search Results for author: Raymond Veldhuis

Found 17 papers, 9 papers with code

E2F-Net: Eyes-to-Face Inpainting via StyleGAN Latent Space

1 code implementation18 Mar 2024 Ahmad Hassanpour, Fatemeh Jamalbafrani, Bian Yang, Kiran Raja, Raymond Veldhuis, Julian Fierrez

We further improve the StyleGAN output to find the optimal code in the latent space using a new optimization for GAN inversion technique.

Face Recognition Facial Inpainting +1

NeutrEx: A 3D Quality Component Measure on Facial Expression Neutrality

no code implementations19 Aug 2023 Marcel Grimmer, Christian Rathgeb, Raymond Veldhuis, Christoph Busch

Accurate face recognition systems are increasingly important in sensitive applications like border control or migration management.

3D Face Reconstruction Face Recognition +1

DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning

1 code implementation12 Aug 2023 Shunxin Wang, Christoph Brune, Raymond Veldhuis, Nicola Strisciuglio

We propose a data augmentation strategy, named DFM-X, that leverages knowledge about frequency shortcuts, encoded in Dominant Frequencies Maps computed for image classification models.

Data Augmentation Image Classification

Defocus Blur Synthesis and Deblurring via Interpolation and Extrapolation in Latent Space

1 code implementation28 Jul 2023 Ioana Mazilu, Shunxin Wang, Sven Dummer, Raymond Veldhuis, Christoph Brune, Nicola Strisciuglio

We train autoencoders with implicit and explicit regularization techniques to enforce linearity relations among the representations of different blur levels in the latent space.

Data Augmentation Deblurring +1

What do neural networks learn in image classification? A frequency shortcut perspective

1 code implementation ICCV 2023 Shunxin Wang, Raymond Veldhuis, Christoph Brune, Nicola Strisciuglio

Our results demonstrate that NNs tend to find simple solutions for classification, and what they learn first during training depends on the most distinctive frequency characteristics, which can be either low- or high-frequencies.

Data Augmentation Image Classification +1

A Survey on the Robustness of Computer Vision Models against Common Corruptions

1 code implementation10 May 2023 Shunxin Wang, Raymond Veldhuis, Christoph Brune, Nicola Strisciuglio

The performance of computer vision models are susceptible to unexpected changes in input images, known as common corruptions (e. g. noise, blur, illumination changes, etc.

Data Augmentation Knowledge Distillation +1

Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks

1 code implementation10 Mar 2023 Zahra Atashgahi, Xuhao Zhang, Neil Kichler, Shiwei Liu, Lu Yin, Mykola Pechenizkiy, Raymond Veldhuis, Decebal Constantin Mocanu

Feature selection that selects an informative subset of variables from data not only enhances the model interpretability and performance but also alleviates the resource demands.

feature selection

Memory-free Online Change-point Detection: A Novel Neural Network Approach

1 code implementation8 Jul 2022 Zahra Atashgahi, Decebal Constantin Mocanu, Raymond Veldhuis, Mykola Pechenizkiy

We show that ALACPD, on average, ranks first among state-of-the-art CPD algorithms in terms of quality of the time series segmentation, and it is on par with the best performer in terms of the accuracy of the estimated change-points.

Change Point Detection Time Series +1

Worst-Case Morphs: a Theoretical and a Practical Approach

no code implementations30 Nov 2021 Una M. Kelly, Raymond Veldhuis, Luuk Spreeuwers

Face Recognition (FR) systems have been shown to be vulnerable to morphing attacks.

Face Recognition

A survey of face recognition techniques under occlusion

no code implementations19 Jun 2020 Dan Zeng, Raymond Veldhuis, Luuk Spreeuwers

As a part of this review, we introduce face detection under occlusion, a preliminary step in face recognition.

Face Detection Face Recognition

A Brain-inspired Algorithm for Training Highly Sparse Neural Networks

2 code implementations17 Mar 2019 Zahra Atashgahi, Joost Pieterse, Shiwei Liu, Decebal Constantin Mocanu, Raymond Veldhuis, Mykola Pechenizkiy

Concretely, by exploiting the cosine similarity metric to measure the importance of the connections, our proposed method, Cosine similarity-based and Random Topology Exploration (CTRE), evolves the topology of sparse neural networks by adding the most important connections to the network without calculating dense gradient in the backward.

Learning Theory

Predicting Face Recognition Performance Using Image Quality

no code implementations24 Oct 2015 Abhishek Dutta, Raymond Veldhuis, Luuk Spreeuwers

This paper proposes a data driven model to predict the performance of a face recognition system based on image quality features.

Face Recognition

Can Facial Uniqueness be Inferred from Impostor Scores?

no code implementations23 Oct 2013 Abhishek Dutta, Raymond Veldhuis, Luuk Spreeuwers

In Biometrics, facial uniqueness is commonly inferred from impostor similarity scores.

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