Domain adaptation in application to gravitational lens finding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Parul, Hanna, Gleyzer, Sergei, Reddy, Pranath, Toomey, Michael W.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912055265591296
author Parul, Hanna
Gleyzer, Sergei
Reddy, Pranath
Toomey, Michael W.
author_facet Parul, Hanna
Gleyzer, Sergei
Reddy, Pranath
Toomey, Michael W.
contents The next decade is expected to see a tenfold increase in the number of strong gravitational lenses, driven by new wide-field imaging surveys. To discover these rare objects, efficient automated detection methods need to be developed. In this work, we assess the performance of three domain adaptation techniques -- Adversarial Discriminative Domain Adaptation (ADDA), Wasserstein Distance Guided Representation Learning (WDGRL), and Supervised Domain Adaptation (SDA) -- in enhancing lens-finding algorithms trained on simulated data when applied to observations from the Hyper Suprime-Cam Subaru Strategic Program. We find that WDGRL combined with an ENN-based encoder provides the best performance in an unsupervised setting and that supervised domain adaptation is able to enhance the model's ability to distinguish between lenses and common similar-looking false positives, such as spiral galaxies, which is crucial for future lens surveys.
format Preprint
id arxiv_https___arxiv_org_abs_2410_01203
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Domain adaptation in application to gravitational lens finding
Parul, Hanna
Gleyzer, Sergei
Reddy, Pranath
Toomey, Michael W.
Instrumentation and Methods for Astrophysics
Cosmology and Nongalactic Astrophysics
The next decade is expected to see a tenfold increase in the number of strong gravitational lenses, driven by new wide-field imaging surveys. To discover these rare objects, efficient automated detection methods need to be developed. In this work, we assess the performance of three domain adaptation techniques -- Adversarial Discriminative Domain Adaptation (ADDA), Wasserstein Distance Guided Representation Learning (WDGRL), and Supervised Domain Adaptation (SDA) -- in enhancing lens-finding algorithms trained on simulated data when applied to observations from the Hyper Suprime-Cam Subaru Strategic Program. We find that WDGRL combined with an ENN-based encoder provides the best performance in an unsupervised setting and that supervised domain adaptation is able to enhance the model's ability to distinguish between lenses and common similar-looking false positives, such as spiral galaxies, which is crucial for future lens surveys.
title Domain adaptation in application to gravitational lens finding
topic Instrumentation and Methods for Astrophysics
Cosmology and Nongalactic Astrophysics
url https://arxiv.org/abs/2410.01203