Related papers: Segmenting proto-halos with vision transformers

Vision-transformers (ViTs) and large-scale convolution-neural-networks (CNNs) have reshaped computer vision through pretrained feature representations that enable strong transfer learning for diverse tasks. However, their efficiency as…

Dark matter substructures are interesting since they can reveal the properties of dark matter. Collisionless N-body simulations of cold dark matter show more substructures compared with the population of dwarf galaxy satellites observed in…

For many analyses in cosmology it is necessary to reconstruct the likely distribution of unobserved fields, such as dark matter or non-luminous baryons, from observed luminous tracers. The dominant approach in cosmology has been to use the…

The first dark matter halos form by direct collapse from peaks in the matter density field, and evidence from numerical simulations and other analyses suggests that the dense inner regions of these objects largely persist today. These halos…

Protohalos, primordial regions in the initial cosmic density field that evolve into dark matter halos, are crucial for understanding cosmic structure formation. Motivated by the potential to reconstruct protohalo positions and shapes from…

Vision transformers are effective deep learning models for vision tasks, including medical image segmentation. However, they lack efficiency and translational invariance, unlike convolutional neural networks (CNNs). To model long-range…

Introduction: The present study on the development and evaluation of an automated brain tumor segmentation technique based on deep learning using the 3D U-Net model. Objectives: The objective is to leverage state-of-the-art convolutional…

This paper presents Discriminative Part Network (DP-Net), a deep architecture with strong interpretation capabilities, which exploits a pretrained Convolutional Neural Network (CNN) combined with a part-based recognition module. This system…

We propose unitary group convolutions (UGConvs), a building block for CNNs which compose a group convolution with unitary transforms in feature space to learn a richer set of representations than group convolution alone. UGConvs generalize…

Within the world of machine learning there exists a wide range of different methods with respective advantages and applications. This paper seeks to present and discuss one such method, namely Convolutional Neural Networks (CNNs). CNNs are…

When solving a segmentation task, shaped-base methods can be beneficial compared to pixelwise classification due to geometric understanding of the target object as shape, preventing the generation of anatomical implausible predictions in…

Transfer learning (TL) for medical image segmentation helps deep learning models achieve more accurate performances when there are scarce medical images. This study focuses on completing segmentation of the ribs from lung ultrasound images…

Disentangling the stellar population in the central galaxy from the intrahalo light can help us shed light on the formation history of the host halo, as the properties of the stellar components are expected to retain traces of its formation…

Today, deep convolutional neural networks (CNNs) have demonstrated state of the art performance for supervised medical image segmentation, across various imaging modalities and tasks. Despite early success, segmentation networks may still…

In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However,…

This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape represented as a point cloud into primitive patches. The key to deep primitive segmentation is learning a feature representation that can separate points…

Deep convolutional networks (CNNs) have exhibited their potential in image inpainting for producing plausible results. However, in most existing methods, e.g., context encoder, the missing parts are predicted by propagating the surrounding…

We develop a method to identify proto-clusters based on dark matter halos represented by galaxy groups selected from surveys of galaxies at high redshift. We test the performance of this method on halos in N-body simulations, and find it…

The peculiar velocities of dark matter halos are crucial to study many issues in cosmology and galaxy evolution. In this study, by using the state-of-the-art deep learning technique, a UNet-based neural network, we propose to reconstruct…

We present a method to numerically estimate the densities of a discretely sampled data based on binary space partitioning tree. We start with a root node containing all the particles and then recursively divide each node into two nodes each…