Search Results for author:
Found 19 papers, 5 papers with code
Adapting the Hypersphere Loss Function from Anomaly Detection to Anomaly Segmentation
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.
Moving Frame Net: SE(3)-Equivariant Network for Volumes
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).
Scale Equivariant U-Net
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.
Morphological adjunctions represented by matrices in max-plus algebra for signal and image processing
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.
Fully trainable Gaussian derivative convolutional layer
The Gaussian kernel and its derivatives have already been employed for Convolutional Neural Networks in several previous works.
MorphoActivation: Generalizing ReLU activation function by mathematical morphology
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.
Differential invariants for SE(2)-equivariant networks
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.
Near out-of-distribution detection for low-resolution radar micro-Doppler signatures
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.
Paris-CARLA-3D: A Real and Synthetic Outdoor Point Cloud Dataset for Challenging Tasks in 3D Mapping
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.
From Unsupervised to Semi-supervised Anomaly Detection Methods for HRRP Targets
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.
Deep Random Projection Outlyingness for Unsupervised Anomaly Detection
The performance of the proposed neural network approach is comparable to a state-of-the-art anomaly detection method.
Scale Equivariant Neural Networks with Morphological Scale-Spaces
The translation equivariance of convolutions can make convolutional neural networks translation equivariant or invariant.
Road Segmentation on low resolution Lidar point clouds for autonomous vehicles
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.
Dealing with Topological Information within a Fully Convolutional Neural Network
A fully convolutional neural network has a receptive field of limited size and therefore cannot exploit global information, such as topological information.
Part-based approximations for morphological operators using asymmetric auto-encoders
This paper addresses the issue of building a part-based representation of a dataset of images.
Max-plus Operators Applied to Filter Selection and Model Pruning in Neural Networks
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.
Segmentation hiérarchique faiblement supervisée
Image segmentation is the process of partitioning an image into a set of meaningful regions according to some criteria.
Prior-based Hierarchical Segmentation Highlighting Structures of Interest
Image segmentation is the process of partitioning an image into a set of meaningful regions according to some criteria.
Automatic Selection of Stochastic Watershed Hierarchies
A coarser partition is obtained by merging adjacent regions of a finer partition.
