no code implementations • 14 May 2023 • Matej Ulicny, Vladimir A. Krylov, Julie Connelly, Rozenn Dahyot
We propose a pipeline for combined multi-class object geolocation and height estimation from street level RGB imagery, which is considered as a single available input data modality.
1 code implementation • 18 Jan 2023 • Jérémy Chopin, Jean-Baptiste Fasquel, Harold Mouchère, Rozenn Dahyot, Isabelle Bloch
On FASSEG data, results show that our module improves accuracy of the CNN by about 6. 3% (the Hausdorff distance decreases from 22. 11 to 20. 71).
1 code implementation • 23 Oct 2022 • Rozenn Dahyot
We propose to directly compute classification estimates by learning features encoded with their class scores using PCA.
1 code implementation • 8 Nov 2021 • Ali Karaali, Rozenn Dahyot, Donal J. Sexton
Accurate retinal vessel segmentation is an important task for many computer-aided diagnosis systems.
no code implementations • 13 Aug 2021 • Chao-Jung Liu, Matej Ulicny, Michael Manzke, Rozenn Dahyot
Localization of street objects from images has gained a lot of attention in recent years.
no code implementations • 13 Aug 2021 • Chao-Jung Liu, Vladimir Krylov, Rozenn Dahyot
In this paper we propose an approach to perform semantic segmentation of 3D point cloud data by importing the geographic information from a 2D GIS layer (OpenStreetMap).
no code implementations • 18 Feb 2021 • Hana Alghamdi, Rozenn Dahyot
We propose a new method with $\mathcal{L}_2$ distance that maps one $N$-dimensional distribution to another, taking into account available information about correspondences.
1 code implementation • 22 Oct 2020 • Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
We show how parameter redundancy in Convolutional Neural Network (CNN) filters can be effectively reduced by pruning in spectral domain.
no code implementations • 15 Jun 2020 • Hana Alghamdi, Rozenn Dahyot
We propose a new method with Nadaraya-Watson that maps one N-dimensional distribution to another taking into account available information about correspondences.
no code implementations • 18 May 2020 • Hana Alghamdi, Rozenn Dahyot
We propose a new colour transfer method with Optimal Transport (OT) to transfer the colour of a sourceimage to match the colour of a target image of the same scene that may exhibit large motion changes betweenimages.
1 code implementation • 18 Jan 2020 • Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space.
Ranked #452 on Image Classification on ImageNet
no code implementations • 9 Jan 2020 • Andrew Anderson, Jing Su, Rozenn Dahyot, David Gregg
Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems.
no code implementations • 29 May 2019 • Rozenn Dahyot, Hana Alghamdi, Mairead Grogan
Grogan et al [11, 12] have recently proposed a solution to colour transfer by minimising the Euclidean distance L2 between two probability density functions capturing the colour distributions of two images (palette and target).
1 code implementation • 30 Apr 2019 • Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
In the context of reverting to preset filters, we propose here a computationally efficient harmonic block that uses Discrete Cosine Transform (DCT) filters in CNNs.
Ranked #34 on Image Classification on STL-10
1 code implementation • 7 Dec 2018 • Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space.
1 code implementation • 28 Aug 2017 • Vladimir A. Krylov, Eamonn Kenny, Rozenn Dahyot
Many applications such as autonomous navigation, urban planning and asset monitoring, rely on the availability of accurate information about objects and their geolocations.
no code implementations • 25 Aug 2017 • Mairéad Grogan, Rozenn Dahyot
We propose several cost functions for registration of shapes encoded with Euclidean and/or non-Euclidean information (unit vectors).
1 code implementation • 17 May 2017 • Mairéad Grogan, Rozenn Dahyot
We present a flexible approach to colour transfer inspired by techniques recently proposed for shape registration.