CoChat
Sign Up
Cited by 137Galaxies: Formation, Evolution, PhenomenaAdvanced Neural Network ApplicationsStellar, planetary, and galactic studies

Using transfer learning to detect galaxy mergers

Open access
Ackermann, Sandro, Schawinski, Kevin, Zhang, Ce, Weigel, Anna K, Turp, M Dennis·2018·Monthly Notices of the Royal Astronomical Society
DOI 10.1093/mnras/sty1398
Open this paper in CoChat — free accountOpen PDF

Abstract

We investigate the use of deep convolutional neural networks (deep CNNs) for automatic visual detection of galaxy mergers. Moreover, we investigate the use of transfer learning in conjunction with CNNs by retraining networks first trained on pictures of everyday objects. We test the hypothesis that transfer learning is useful for improving classification performance for small training sets. This would make transfer learning useful for finding rare objects in astronomical imaging data sets. We find that these deep learning methods perform significantly better than current state-of-the-art merger detection methods based on non-parametric systems such as CAS and GM20. Our method is end-to-end and robust to image noise and distortions; it can be applied directly without image preprocessing. We also find that transfer learning can act as a regularizer in some cases, leading to better overall classification accuracy (p = 0.02). Transfer learning on our full training set leads to a lowered error rate from 0.038 ± 1 to 0.032 ± 1, a relative improvement of 15 per cent. Finally, we perform a basic sanity-check by creating a merger sample with our method, and comparing with an already existing, manually created merger catalogue in terms of colour--mass distribution and stellar mass function.

Integrity signals

Registry

Crossref · 10.1093/mnras/sty1398

Cites

61 of 61 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Ackermann et al. (2018) reported significant improvements over state-of-the-art approaches for classifying galaxy mergers.

    “Ackermann et al. (2018) made the first tests to classify galaxy mergers trained on Galaxy Zoo and reported significant improvements over state-ofthe-art approaches”

    From The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys (2023) · cites this paper as Ackermann et al. (2018)

  • Reliable results can be obtained with small training samples.

    “Some works (e.g. Ackermann et al. 2018; Walmsley et al. 2019) have demonstrated that reliable results can be obtained with small training samples.”

    From The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys (2023) · cites this paper as Ackermann et al. 2018

Cites

Flagged first, then by citations

3 of the 64 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Related

Authors
Ackermann, S., Schawinski, K., Zhang, C., Weigel, A. K., & Turp, M. D.
Affiliations
ETH Zurich (CH)
Corresponding author
  • Ackermann, Sandro
  • Schawinski, Kevin
ORCID
Venue
Monthly Notices of the Royal Astronomical Society
Publisher
Oxford University Press (OUP)
Published
2018-05-28
Volume
479
Issue
1
Pages
415-425
ISSN
  • 0035-8711 (ISSN-L)
  • 1365-2966
DOI
10.1093/mnras/sty1398
OpenAlex
W2804191040
Cited by
137
References
64
Citations by year
2026: 7 · 2025: 13 · 2024: 18 · 2023: 20 · 2022: 19 · 2021: 20 · 2020: 14 · 2019: 22 · 2018: 4
FWCI
8.05
Type
journal article
Language
en
Open access
Licence
academic.oup.com/journals/pages/about_us/legal/notices (vor)
Locations
  • Monthly Notices of the Royal Astronomical Society (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Repository for Publications and Research Data (ETH Zurich) (submittedVersion, other-oa)
  • arXiv (Cornell University)
  • ETH Zürich Research Collection
Funders
Swiss National Science Foundation (PP00P2_138979, PP00P2_166159, 75 407540_167266)
Topics
  • Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Galaxies: Formation, Evolution, Phenomena
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Stellar, planetary, and galactic studies
Keywords
galaxy mergers, transfer learning, convolutional neural networks, astronomical image classification, limited training data, image noise robustness, regularizers, stellar mass function

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review