154 citations · 334 across the 20 of their papers we have counts for
23 papers
Graph neural networks for sampling-invariant embeddings of organized signal sets
Martin Bauw, Santiago Velasco-Forero, Jesus Angulo
Sensor networks and radars can deliver signals as organized sets, e.g. ordered signals, signals describing range cells within a grid or signals perceived as graph nodes. Within suc…
Adapting the Hypersphere Loss Function from Anomaly Detection to Anomaly Segmentation
Joao P. C. Bertoldo, Santiago Velasco-Forero, Jesus Angulo +1
We propose an incremental improvement to Fully Convolutional Data Description (FCDD), an adaptation of the one-class classification approach from anomaly detection to image anomaly…
Moving Frame Net: SE(3)-Equivariant Network for Volumes
Mateus Sangalli, Samy Blusseau, Santiago Velasco-Forero +1
Equivariance of neural networks to transformations helps to improve their performance and reduce generalization error in computer vision tasks, as they apply to datasets presenting…
Scale Equivariant U-Net
Mateus Sangalli, Samy Blusseau, Santiago Velasco-Forero +1
In neural networks, the property of being equivariant to transformations improves generalization when the corresponding symmetry is present in the data. In particular, scale-equiva…
Differential invariants for SE(2)-equivariant networks
Mateus Sangalli, Samy Blusseau, Santiago Velasco-Forero +1
Symmetry is present in many tasks in computer vision, where the same class of objects can appear transformed, e.g. rotated due to different camera orientations, or scaled due to pe…
Fully trainable Gaussian derivative convolutional layer
Valentin Penaud--Polge, Santiago Velasco-Forero, Jesus Angulo
The Gaussian kernel and its derivatives have already been employed for Convolutional Neural Networks in several previous works. Most of these papers proposed to compute filters by…
MorphoActivation: Generalizing ReLU activation function by mathematical morphology
Santiago Velasco-Forero, Jesús Angulo
This paper analyses both nonlinear activation functions and spatial max-pooling for Deep Convolutional Neural Networks (DCNNs) by means of the algebraic basis of mathematical morph…
Morphological adjunctions represented by matrices in max-plus algebra for signal and image processing
Samy Blusseau, Santiago Velasco-Forero, Jesus Angulo +1
In discrete signal and image processing, many dilations and erosions can be written as the max-plus and min-plus product of a matrix on a vector. Previous studies considered operat…
Near out-of-distribution detection for low-resolution radar micro-Doppler signatures
Martin Bauw, Santiago Velasco-Forero, Jesus Angulo +2
Near out-of-distribution detection (OODD) aims at discriminating semantically similar data points without the supervision required for classification. This paper puts forward an OO…
Paris-CARLA-3D: A Real and Synthetic Outdoor Point Cloud Dataset for Challenging Tasks in 3D Mapping
Jean-Emmanuel Deschaud, David Duque, Jean Pierre Richa +3
Paris-CARLA-3D is a dataset of several dense colored point clouds of outdoor environments built by a mobile LiDAR and camera system. The data are composed of two sets with syntheti…
ICLR 2021 Challenge for Computational Geometry & Topology: Design and Results
Nina Miolane, Matteo Caorsi, Umberto Lupo +30
This paper presents the computational challenge on differential geometry and topology that happened within the ICLR 2021 workshop "Geometric and Topological Representation Learning…
Deep Random Projection Outlyingness for Unsupervised Anomaly Detection
Martin Bauw, Santiago Velasco-Forero, Jesus Angulo +2
Random projection is a common technique for designing algorithms in a variety of areas, including information retrieval, compressive sensing and measuring of outlyingness. In this…
From Unsupervised to Semi-supervised Anomaly Detection Methods for HRRP Targets
Martin Bauw, Santiago Velasco-Forero, Jesus Angulo +2
Responding to the challenge of detecting unusual radar targets in a well identified environment, innovative anomaly and novelty detection methods keep emerging in the literature. T…
Scale Equivariant Neural Networks with Morphological Scale-Spaces
Mateus Sangalli, Samy Blusseau, Santiago Velasco-Forero +1
The translation equivariance of convolutions can make convolutional neural networks translation equivariant or invariant. Equivariance to other transformations (e.g. rotations, aff…
Road Segmentation on low resolution Lidar point clouds for autonomous vehicles
Leonardo Gigli, B Ravi Kiran, Thomas Paul +4
Point cloud datasets for perception tasks in the context of autonomous driving often rely on high resolution 64-layer Light Detection and Ranging (LIDAR) scanners. They are expensi…
Dealing with Topological Information within a Fully Convolutional Neural Network
Etienne Decencière, Santiago Velasco-Forero, Fu Min +6
A fully convolutional neural network has a receptive field of limited size and therefore cannot exploit global information, such as topological information. A solution is proposed…
Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks
Yunxiang Zhang, Samy Blusseau, Santiago Velasco-Forero +2
Following recent advances in morphological neural networks, we propose to study in more depth how Max-plus operators can be exploited to define morphological units and how they beh…
Part-based approximations for morphological operators using asymmetric auto-encoders
Bastien Ponchon, Santiago Velasco-Forero, Samy Blusseau +2
This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a r…
The Strong Gravitational Lens Finding Challenge
R. Benton Metcalf, M. Meneghetti, Camille Avestruz +33
Large scale imaging surveys will increase the number of galaxy-scale strong lensing candidates by maybe three orders of magnitudes beyond the number known today. Finding these rare…
Deep learning for galaxy surface brightness profile fitting
D. Tuccillo, M. Huertas-Company, E. Decencière +3
Numerous ongoing and future large area surveys (e.g. DES, EUCLID, LSST, WFIRST), will increase by several orders of magnitude the volume of data that can be exploited for galaxy mo…
Prior-based Hierarchical Segmentation Highlighting Structures of Interest
Amin Fehri, Santiago Velasco-Forero, Fernand Meyer
Image segmentation is the process of partitioning an image into a set of meaningful regions according to some criteria. Hierarchical segmentation has emerged as a major trend in th…
Deep learning for studies of galaxy morphology
D. Tuccillo, M. Huertas-Company, E. Decenciere +1
Establishing accurate morphological measurements of galaxies in a reasonable amount of time for future big-data surveys such as EUCLID, the Large Synoptic Survey Telescope or the W…
Automatic Selection of Stochastic Watershed Hierarchies
Amin Fehri, Santiago Velasco-Forero, Fernand Meyer
The segmentation, seen as the association of a partition with an image, is a difficult task. It can be decomposed in two steps: at first, a family of contours associated with a ser…