1 code implementation • 4 Mar 2024 • Puru Vaish, Shunxin Wang, Nicola Strisciuglio
However, common visual augmentations might not guarantee extensive robustness of computer vision models.
no code implementations • 6 Feb 2024 • Adjorn van Engelenhoven, Nicola Strisciuglio, Estefanía Talavera
The self-attention from within each cluster is then combined with the cluster summaries of other clusters, enabling information flow across the entire input sequence.
no code implementations • 29 Jan 2024 • María Leyva-Vallina, Nicola Strisciuglio, Nicolai Petkov
Visual place recognition is a critical task in computer vision, especially for localization and navigation systems.
no code implementations • 8 Dec 2023 • Pablo Laso, Stefano Cerri, Annabel Sorby-Adams, Jennifer Guo, Farrah Mateen, Philipp Goebl, Jiaming Wu, Peirong Liu, Hongwei Li, Sean I. Young, Benjamin Billot, Oula Puonti, Gordon Sze, Sam Payabavash, Adam DeHavenon, Kevin N. Sheth, Matthew S. Rosen, John Kirsch, Nicola Strisciuglio, Jelmer M. Wolterink, Arman Eshaghi, Frederik Barkhof, W. Taylor Kimberly, Juan Eugenio Iglesias
Brain atrophy and white matter hyperintensity (WMH) are critical neuroimaging features for ascertaining brain injury in cerebrovascular disease and multiple sclerosis.
1 code implementation • 12 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.
1 code implementation • 28 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.
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.
no code implementations • 22 May 2023 • Sven Dummer, Nicola Strisciuglio, Christoph Brune
In this work, we focus on a limitation of neural network-based atlas building and statistical latent modeling methods, namely that they either are (i) resolution dependent or (ii) disregard any data/problem-specific geometry needed for proper mean-variance analysis.
1 code implementation • 10 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.
1 code implementation • CVPR 2023 • Maria Leyva-Vallina, Nicola Strisciuglio, Nicolai Petkov
Motivated by the fact that two images of the same place only partially share visual cues due to camera pose differences, we deploy an automatic re-annotation strategy to re-label VPR datasets.
Ranked #1 on Visual Place Recognition on MSLS
no code implementations • 11 Mar 2022 • Stefan Haller, Adina Aldea, Christin Seifert, Nicola Strisciuglio
We complement previous surveys by providing a comprehensive analysis of recently published methods that deploy deep learning approaches.
1 code implementation • Journal of Computational Science 2021 • Virginia Riego, Lidia Sánchez-González, Laura Fernández-Robles, Alexis Gutiérrez-Fernández, Nicola Strisciuglio
Machined workpieces must satisfy quality standards such as avoid the presence of burrs in edge finishing to reduce production costs and time.
Ranked #1 on Classification on Burr classification images
1 code implementation • 11 Mar 2021 • María Leyva-Vallina, Nicola Strisciuglio, Nicolai Petkov
We propose a Generalized Contrastive loss (GCL) function that relies on image similarity as a continuous measure, and use it to train a siamese CNN.
Ranked #3 on Visual Place Recognition on Mapillary test
no code implementations • 2 Mar 2021 • Nicola Strisciuglio
These findings inspired researchers in image processing and computer vision to deploy such models to solve problems of visual data processing.
no code implementations • 1 Jan 2021 • Nicola Strisciuglio, George Azzopardi, Nicolai Petkov
The rectified responses of the push and pull filter pairs are then combined by a linear function.
1 code implementation • 27 Jun 2020 • Rafael Brandt, Nicola Strisciuglio, Nicolai Petkov
Efficient yet accurate extraction of depth from stereo image pairs is required by systems with low power resources, such as robotics and embedded systems.
no code implementations • 28 Jun 2019 • Maria Leyva-Vallina, Nicola Strisciuglio, Nicolai Petkov
In this paper we propose an extended version of the TB-Places data set, which is designed for testing algorithms for visual place recognition.
no code implementations • 29 Jan 2019 • Nicola Strisciuglio, Manuel Lopez-Antequera, Nicolai Petkov
We propose a new layer in Convolutional Neural Networks (CNNs) to increase their robustness to several types of noise perturbations of the input images.
no code implementations • 21 Jan 2019 • Nicola Strisciuglio, Mario Vento, Nicolai Petkov
We construct a set of COPE feature extractors, configured on a number of training patterns.
1 code implementation • 26 Nov 2018 • Nicola Strisciuglio, George Azzopardi, Nicolai Petkov
This type of inhibition allows for sharper detection of the patterns of interest and improves the quality of delineation especially in images with spurious texture.
no code implementations • 2 Jan 2018 • Nicola Strisciuglio
Recent advancements in pattern recognition and signal processing concern the automatic learning of data representations from labeled training samples.
no code implementations • 2 Aug 2017 • Alessia Saggese, Nicola Strisciuglio, Mario Vento, Nicolai Petkov
Starting from this consideration, we propose a trainable pose detector, that can be configured on a prototype skeleton in an automatic configuration process.
no code implementations • 24 Jul 2017 • Nicola Strisciuglio, George Azzopardi, Nicolai Petkov
The detection of curvilinear structures is an important step for various computer vision applications, ranging from medical image analysis for segmentation of blood vessels, to remote sensing for the identification of roads and rivers, and to biometrics and robotics, among others.
no code implementations • 24 Jul 2017 • Nicola Strisciuglio, Nicolai Petkov
Delineation of line patterns in images is a basic step required in various applications such as blood vessel detection in medical images, segmentation of rivers or roads in aerial images, detection of cracks in walls or pavements, etc.
no code implementations • 29 Mar 2017 • Estefania Talavera, Nicola Strisciuglio, Nicolai Petkov, Petia Radeva
Lifelogging is a process of collecting rich source of information about daily life of people.