Related papers: DeepVoid: A Deep Learning Void Detector

Dark matter haloes play a fundamental role in cosmological structure formation. The most common approach to model their assembly mechanisms is through N-body simulations. In this work we present an innovative pathway to predict dark matter…

Learning useful representations of complex data has been the subject of extensive research for many years. With the diffusion of Deep Neural Networks, Variational Autoencoders have gained lots of attention since they provide an explicit…

Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also…

The modeling of realistic magnetic materials requires the inclusion of defects. Based on the pseudospectral Landau-Lifshitz description of magnetisation dynamics, we propose a statistical model that takes into account defects, specifically…

Deep neural networks are susceptible to generating overconfident yet erroneous predictions when presented with data beyond known concepts. This challenge underscores the importance of detecting out-of-distribution (OOD) samples in the open…

DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer vision. DeepLab2 includes all our recently developed…

Collision detection is essential to virtually all robotics applications. However, traditional geometric collision detection methods generally require pre-existing workspace geometry representations; thus, they are unable to infer the…

We present a novel graph-based machine learning classifier for identifying the dark matter cosmic web environments of galaxies. Large galaxy surveys offer comprehensive statistical views of how galaxy properties are shaped by large-scale…

Cosmic voids are effective cosmological probes to discriminate among competing world models. Their identification is generally based on density or geometry criteria that, because of their very nature, are prone to shot noise. We propose two…

We propose a novel semantic segmentation algorithm by learning a deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and…

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution. In the last decade, deep learning…

This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the…

Cosmic voids are key elements in our understanding of the large-scale structure of the Universe. They are crucial to constrain cosmological parameters, understand the structure formation and evolution of our Universe, and they could also be…

We investigate and demonstrate the use of convolutional neural networks (CNNs) for the task of distinguishing between merging and non-merging galaxies in simulated images, and for the first time at high redshifts (i.e. $z=2$). We extract…

Computed Tomography Angiography is a key modality providing insights into the cerebrovascular vessel tree that are crucial for the diagnosis and treatment of ischemic strokes, in particular in cases of large vessel occlusions (LVO). Thus,…

In this paper we study the problem of learning the weights of a deep convolutional neural network. We consider a network where convolutions are carried out over non-overlapping patches with a single kernel in each layer. We develop an…

Strong gravitational lensing is a promising probe of the substructure of dark matter halos. Deep learning methods have the potential to accurately identify images containing substructure, and differentiate WIMP dark matter from other well…

Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012). The winning model on the…

In this paper, we study the task of detecting semantic parts of an object, e.g., a wheel of a car, under partial occlusion. We propose that all models should be trained without seeing occlusions while being able to transfer the learned…

We present VIDE, the Void IDentification and Examination toolkit, an open-source Python/C++ code for finding cosmic voids in galaxy redshift surveys and N-body simulations, characterizing their properties, and providing a platform for more…