no code implementations • 17 Jul 2023 • Tin Barisin, Jesus Angulo, Katja Schladitz, Claudia Redenbach
In this work, we define an alternative feature representation based on the Riesz transform.
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.
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.
1 code implementation • 14 Jun 2021 • Yufei Hu, Nacim Belkhir, Jesus Angulo, Angela Yao, Gianni Franchi
Using a combination of linear and non-linear procedures is critical for generating a sufficiently deep feature space.
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 • 4 May 2021 • Jesus Angulo
Indeed, I firmly believe that the convergence between mathematical morphology and the computation methods which gravitate around deep learning (fully connected networks, convolutional neural networks, residual neural networks, recurrent neural networks, etc.)
1 code implementation • 19 Feb 2021 • Alexandre Kirszenberg, Guillaume Tochon, Elodie Puybareau, Jesus Angulo
Integrating mathematical morphology operations within deep neural networks has been subject to increasing attention lately.
no code implementations • 2 Oct 2020 • Guillaume Noyel, Jesus Angulo, Dominique Jeulin
The present paper develops a general methodology for the morphological segmentation of hyperspectral images, i. e., with an important number of channels.
no code implementations • 28 Oct 2019 • Guillaume Noyel, Jesus Angulo, Dominique Jeulin, Daniel Balvay, Charles-André Cuenod
A full multivariate segmentation method based on dimensionality reduction, noise filtering, supervised classification and stochastic watershed is explained and tested on several data sets.
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 • 29 Nov 2018 • Jean Serra, Jesus Angulo, B Ravi Kiran
Consider a family $Z=\{\boldsymbol{x_{i}}, y_{i}$,$1\leq i\leq N\}$ of $N$ pairs of vectors $\boldsymbol{x_{i}} \in \mathbb{R}^d$ and scalars $y_{i}$ that we aim to predict for a new sample vector $\mathbf{x}_0$.
no code implementations • 30 May 2016 • Gianni Franchi, Jesus Angulo, Dino Sejdinovic
We propose a novel approach for pixel classification in hyperspectral images, leveraging on both the spatial and spectral information in the data.
no code implementations • 9 Feb 2016 • Guillaume Noyel, Jesus Angulo, Dominique Jeulin
Subsequently, a probability density function (pdf) of contours containing spatial and spectral information is estimated by simulation using a stochastic WS approach driven by the spectral classification.
no code implementations • 2 Feb 2016 • Guillaume Noyel, Jesus Angulo, Dominique Jeulin
Then a finer segmentation is obtained by computing $\eta$-bounded regions and $\mu$-geodesic balls inside the $\lambda$-flat zones.