zoobot-arch-comp
A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification
Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 3 DOI reference(s) in README -
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (7.6%) to scientific vocabulary
Repository
A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification
Basic Info
- Host: GitHub
- Owner: ezrafielding
- License: mit
- Language: Python
- Default Branch: main
- Size: 590 KB
Statistics
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification
Abstract
The classification of galaxy morphology plays a crucial role in understanding galaxy formation and evolution. Traditionally, this process is done manually. The emergence of deep learning techniques has given room for the automation of this process. As such, this paper offers a comparison of deep learning architectures to determine which is best suited for optical galaxy morphology classification. Adapting the model training method proposed by Walmsley et al in 2021, the Zoobot Python library is used to train models to predict Galaxy Zoo DECaLS decision tree responses, made by volunteers, using EfficientNet B0, DenseNet121 and ResNet50 as core model architectures. The predicted results are then used to generate accuracy metrics per decision tree question to determine architecture performance. DenseNet121 was found to produce the best results, in terms of accuracy, with a reasonable training time. In future, further testing with more deep learning architectures could prove beneficial.
Zoobot Library
The lastest version of the Zoobot library used in this work can be found here: https://github.com/mwalmsley/zoobot
Citation
E. Fielding, C. N. Nyirenda and M. Vaccari, "A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification," 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), 2021, pp. 1-5, doi: 10.1109/ICECET52533.2021.9698414.
Owner
- Name: Ezra Fielding
- Login: ezrafielding
- Kind: user
- Location: Kitakyushu, Japan
- Company: Kyushu Institute of Technology
- Twitter: ezrafielding
- Repositories: 2
- Profile: https://github.com/ezrafielding
Citation (CITATION.cff)
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: >-
A Comparison of Deep Learning Architectures for Optical
Galaxy Morphology Classification
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Ezra
family-names: Fielding
email: 3869003@myuwc.ac.za
affiliation: University of the Western Cape
orcid: 'https://orcid.org/0000-0002-7936-0222'
- given-names: Clement N.
family-names: Nyirenda
email: cnyirenda@uwc.ac.za
affiliation: University of the Western Cape
orcid: 'https://orcid.org/0000-0002-4181-0478'
- given-names: Mattia
family-names: Vaccari
email: mvaccari@uwc.ac.za
affiliation: University of the Western Cape
orcid: 'https://orcid.org/0000-0002-6748-0577'
identifiers:
- type: doi
value: 10.1109/ICECET52533.2021.9698414
description: The DOI of the work.
- type: doi
value: 10.48550/arXiv.2111.04353
description: The ArXiv deposit of the encompassing paper.
repository-code: 'https://github.com/ezrafielding/zoobot-arch-comp'
url: 'https://sites.google.com/myuwc.ac.za/galaxy-classification'
abstract: >-
The classification of galaxy morphology plays a crucial
role in understanding galaxy formation and evolution.
Traditionally, this process is done manually. The
emergence of deep learning techniques has given room for
the automation of this process. As such, this paper offers
a comparison of deep learning architectures to determine
which is best suited for optical galaxy morphology
classification. Adapting the model training method
proposed by Walmsley et al in 2021, the Zoobot Python
library is used to train models to predict Galaxy Zoo
DECaLS decision tree responses, made by volunteers, using
EfficientNet B0, DenseNet121 and ResNet50 as core model
architectures. The predicted results are then used to
generate accuracy metrics per decision tree question to
determine architecture performance. DenseNet121 was found
to produce the best results, in terms of accuracy, with a
reasonable training time. In future, further testing with
more deep learning architectures could prove beneficial.
license: MIT
date-released: '2021-12-09'
preferred-citation:
type: conference-paper
authors:
- given-names: Ezra
family-names: Fielding
email: 3869003@myuwc.ac.za
affiliation: University of the Western Cape
orcid: 'https://orcid.org/0000-0002-7936-0222'
- given-names: Clement N.
family-names: Nyirenda
email: cnyirenda@uwc.ac.za
affiliation: University of the Western Cape
orcid: 'https://orcid.org/0000-0002-4181-0478'
- given-names: Mattia
family-names: Vaccari
email: mvaccari@uwc.ac.za
affiliation: University of the Western Cape
orcid: 'https://orcid.org/0000-0002-6748-0577'
title: A Comparison of Deep Learning Architectures for Optical Galaxy Morphology Classification
doi: 10.1109/ICECET52533.2021.9698414
pages: 1-5
year: '2021'
conference:
name: 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET)
date-start: "2022-12-09"
date-end: "2022-12-10"