no code implementations • 23 Jan 2023 • Joao P. C. Bertoldo, Santiago Velasco-Forero, Jesus Angulo, Etienne Decencière
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 segmentation (a. k. a.
1 code implementation • 7 Nov 2022 • Mateus Sangalli, Samy Blusseau, Santiago Velasco-Forero, Jesus Angulo
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 symmetries (e. g. scalings, rotations, translations).
no code implementations • 10 Oct 2022 • Mateus Sangalli, Samy Blusseau, Santiago Velasco-Forero, Jesus Angulo
Therefore, this paper introduces the Scale Equivariant U-Net (SEU-Net), a U-Net that is made approximately equivariant to a semigroup of scales and translations through careful application of subsampling and upsampling layers and the use of aforementioned scale-equivariant layers.
no code implementations • 28 Jul 2022 • Samy Blusseau, Santiago Velasco-Forero, Jesus Angulo, Isabelle Bloch
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.
1 code implementation • 18 Jul 2022 • 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.
no code implementations • 13 Jul 2022 • 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 morphology.
1 code implementation • 27 Jun 2022 • Mateus Sangalli, Samy Blusseau, Santiago Velasco-Forero, Jesús Angulo
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 perspective.
2 code implementations • 12 May 2022 • Martin Bauw, Santiago Velasco-Forero, Jesus Angulo, Claude Adnet, Olivier Airiau
We emphasize the relevance of OODD and its specific supervision requirements for the detection of a multimodal, diverse targets class among other similar radar targets and clutter in real-life critical systems.
no code implementations • 22 Nov 2021 • Jean-Emmanuel Deschaud, David Duque, Jean Pierre Richa, Santiago Velasco-Forero, Beatriz Marcotegui, and François Goulette
The data are composed of two sets with synthetic data from the open source CARLA simulator (700 million points) and real data acquired in the city of Paris (60 million points), hence the name Paris-CARLA-3D.
no code implementations • 10 Jun 2021 • Martin Bauw, Santiago Velasco-Forero, Jesus Angulo, Claude Adnet, Olivier Airiau
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.
no code implementations • 8 Jun 2021 • Martin Bauw, Santiago Velasco-Forero, Jesus Angulo, Claude Adnet, Olivier Airiau
The performance of the proposed neural network approach is comparable to a state-of-the-art anomaly detection method.
no code implementations • 4 May 2021 • Mateus Sangalli, Samy Blusseau, Santiago Velasco-Forero, Jesus Angulo
The translation equivariance of convolutions can make convolutional neural networks translation equivariant or invariant.
no code implementations • 27 May 2020 • Leonardo Gigli, B Ravi Kiran, Thomas Paul, Andres Serna, Nagarjuna Vemuri, Beatriz Marcotegui, Santiago Velasco-Forero
In our experiments the low resolution 16/32 layer LIDAR point clouds are simulated by subsampling the original 64 layer data, for subsequent transformation in to a feature map in the Bird-Eye-View (BEV) and SphericalView (SV) representations of the point cloud.
no code implementations • 27 Jun 2019 • Etienne Decencière, Santiago Velasco-Forero, Fu Min, Juanjuan Chen, Hélène Burdin, Gervais Gauthier, Bruno Laÿ, Thomas Bornschloegl, Thérèse Baldeweck
A fully convolutional neural network has a receptive field of limited size and therefore cannot exploit global information, such as topological information.
no code implementations • 20 Mar 2019 • Bastien Ponchon, Santiago Velasco-Forero, Samy Blusseau, Jesus Angulo, Isabelle Bloch
This paper addresses the issue of building a part-based representation of a dataset of images.
1 code implementation • 19 Mar 2019 • Yunxiang Zhang, Samy Blusseau, Santiago Velasco-Forero, Isabelle Bloch, Jesus Angulo
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 behave when incorporated in layers of conventional neural networks.
no code implementations • 20 Feb 2018 • 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.
no code implementations • 9 Mar 2017 • 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.
no code implementations • 9 Sep 2016 • Amin Fehri, Santiago Velasco-Forero, Fernand Meyer
A coarser partition is obtained by merging adjacent regions of a finer partition.