Segmenting proto-halos with vision transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alokda, Toka, Porciani, Cristiano
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915982495186944
author Alokda, Toka
Porciani, Cristiano
author_facet Alokda, Toka
Porciani, Cristiano
contents The formation of dark-matter halos from small cosmological perturbations generated in the early universe is a highly non-linear process typically modeled through N-body simulations. In this work, we explore the use of deep learning to segment and classify proto-halo regions in the initial density field according to their final halo mass at redshift z=0. We compare two architectures: a fully convolutional neural network (CNN) based on the V-Net design and a U-Net transformer. We find that the transformer-based network significantly outperforms the CNN across all metrics, achieving sub-percent error in the total segmented mass per halo class. Both networks deliver much higher accuracy than the perturbation-theory-based model \textsc{pinocchio}, especially at low halo masses and in the detailed reconstruction of proto-halo boundaries. We also investigate the impact of different input features by training models on the density field, the tidal shear, and their combination. Finally, we use Grad-CAM to generate class-activation heatmaps for the CNN, providing preliminary yet suggestive insights into how the network exploits the input fields.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Segmenting proto-halos with vision transformers
Alokda, Toka
Porciani, Cristiano
Cosmology and Nongalactic Astrophysics
Instrumentation and Methods for Astrophysics
Computer Vision and Pattern Recognition
85-08, 68T07
The formation of dark-matter halos from small cosmological perturbations generated in the early universe is a highly non-linear process typically modeled through N-body simulations. In this work, we explore the use of deep learning to segment and classify proto-halo regions in the initial density field according to their final halo mass at redshift z=0. We compare two architectures: a fully convolutional neural network (CNN) based on the V-Net design and a U-Net transformer. We find that the transformer-based network significantly outperforms the CNN across all metrics, achieving sub-percent error in the total segmented mass per halo class. Both networks deliver much higher accuracy than the perturbation-theory-based model \textsc{pinocchio}, especially at low halo masses and in the detailed reconstruction of proto-halo boundaries. We also investigate the impact of different input features by training models on the density field, the tidal shear, and their combination. Finally, we use Grad-CAM to generate class-activation heatmaps for the CNN, providing preliminary yet suggestive insights into how the network exploits the input fields.
title Segmenting proto-halos with vision transformers
topic Cosmology and Nongalactic Astrophysics
Instrumentation and Methods for Astrophysics
Computer Vision and Pattern Recognition
85-08, 68T07
url https://arxiv.org/abs/2508.00049