CoChat
Sign Up
Cited by 781Galaxies: Formation, Evolution, PhenomenaAdvanced Neural Network ApplicationsCell Image Analysis Techniques

Rotation-invariant convolutional neural networks for galaxy morphology prediction

Open access
Dieleman, Sander, Willett, Kyle W., Dambre, Joni·2015·Monthly Notices of the Royal Astronomical Society
DOI 10.1093/mnras/stv632
Open this paper in CoChat — free accountOpen PDF

Abstract

Measuring the morphological parameters of galaxies is a key requirement for studying their formation and evolution. Surveys such as the Sloan Digital Sky Survey have resulted in the availability of very large collections of images, which have permitted population-wide analyses of galaxy morphology. Morphological analysis has traditionally been carried out mostly via visual inspection by trained experts, which is time consuming and does not scale to large (≳104) numbers of images. Although attempts have been made to build automated classification systems, these have not been able to achieve the desired level of accuracy. The Galaxy Zoo project successfully applied a crowdsourcing strategy, inviting online users to classify images by answering a series of questions. Unfortunately, even this approach does not scale well enough to keep up with the increasing availability of galaxy images. We present a deep neural network model for galaxy morphology classification which exploits translational and rotational symmetry. It was developed in the context of the Galaxy Challenge, an international competition to build the best model for morphology classification based on annotated images from the Galaxy Zoo project. For images with high agreement among the Galaxy Zoo participants, our model is able to reproduce their consensus with near-perfect accuracy (>99 per cent) for most questions. Confident model predictions are highly accurate, which makes the model suitable for filtering large collections of images and forwarding challenging images to experts for manual annotation. This approach greatly reduces the experts’ workload without affecting accuracy. The application of these algorithms to larger sets of training data will be critical for analysing results from future surveys such as the Large Synoptic Survey Telescope.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1093/mnras/stv632

Cites

50 of 50 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • CNNs excel at morphological classification of galaxies.

    “Shown most prominently by the winners of the 'Galaxy Challenge' (Dieleman et al. 2015) and numerous subsequent works since (Dom´ ınguez S´ anchez et al. 2018, 2019; Khan et al. 2019; Walmsley et al. 2020; Spindler et al. 2020; Vega-Ferrero et al. 2020), CNNs excel at this task.”

    From Self-supervised Representation Learning for Astronomical Images (2021) · cites this paper as Dieleman et al. 2015

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 20

  1. Bastien F. et al., 2012, Deep Learning and Unsupervised Feature Learning NIPS 2012 Workshop
  2. Bengio Y., 2012, in Montavon G., Orr G., M¨ uller K.-R., eds, Neural Networks: Tricks of the Trade. Springer-Verlag Berlin, p. 437
  3. Bengio Y., Boulanger-Lewandowski N., Pascanu R., 2013, in IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Advances in Optimizing Recurrent Networks. IEEE, New York, p. 8624
  4. Bergstra J. et al., 2010, in St´ efan van der W., Jarrod M., eds, Proc. Python for Scientific Computing Conf. (SciPy), Theano: A CPU and GPU Math Expression Compiler. Austin, TX, p. 3
  5. Bishop C. M., 2006, Pattern Recognition and Machine Learning. Vol. 1. Springer-Verlag, New York
  6. Boureau Y.-L., Ponce J., Lecun Y., 2010, in Johannes F., Thorsten J., eds, Proc. 27th Int. Conf. on Machine Learning, A Theoretical Analysis of Feature Pooling in Visual Recognition. Omnipress, Madison, WI, p. 111
  7. Bruna J., Zaremba W., Szlam A., LeCun Y., 2014, in Yoshua B., Yann L.-C., eds, International Conf. on Learning Representations. Banff, Alberta, Canada Clery D., 2011, Science, 333, 173 Collister A. A., Lahav O., 2004, PASP, 116, 345 Darg D. et al., 2010, MNRAS, 401, 1043 De La Calleja J., Fuentes O., 2004, MNRAS, 349, 87 Firth A. E., Lahav O., Somerville R. S., 2003, MNRAS, 339, 1195 Folkes S., Lahav O., Maddox S., 1996, MNRAS, 283, 651
  8. Glorot X., Bordes A., Bengio Y., 2011, in Gordon G., Dunson D., Dud´ ık M., eds, JMLR Workshop Conf. Proc. Vol. 15: Proc. 14th Int. Conf. on Artificial Intelligence and Statistics (AISTATS 2011), Deep Sparse Rectifier Neural Networks. Journal of Machine Learning Research, jmlr.org, p. 315
  9. Goodfellow I. J., Warde-Farley D., Mirza M., Courville A., Bengio Y., 2013, in Sanjoy D., David Mc.A., eds, Proc. 30th Int. Conf. on Machine Learning, Journal of Machine Learning Research, jmlr.org, p. 1319
  10. Krizhevsky A., Sutskever I., Hinton G. E., 2012, in Pereira F., Burges C. J. C., Bottou L., Weinberger K. Q., eds, Advances in Neural Information Processing Systems 25 (NIPS 2012), Imagenet Classification With Deep Convolutional Neural Networks. Curran Associates, Inc., Red Hook, New York, p. 1097
  11. LeCun Y., Bottou L., Bengio Y., Haffner P., 1998, Proc. IEEE, 86, 2278
  12. Mairal J., Koniusz P., Harchaoui Z., Schmid C., 2014, in Ghahramani Z., Welling M., Cortes C., Lawrence N. D., Weinberger K. Q., eds, Advances in Neural Information Processing Systems 27 (NIPS 2014). Curran As- sociates, Inc., Red Hook, New York, p. 2627
  13. Nair V., Hinton G. E., 2010, in Johannes F., Thorsten J., eds, Proc. 27th Int. Conf. on Machine Learning (ICML-10), Rectified Linear Units Improve Restricted Boltzmann Machines. Omnipress, Madison, WI, p. 807
  14. Polsterer K. L., Gieseke F., Kramer O., 2012, in Ballester P., Egret D., Lorente N. P. F., eds, ASP Conf. Ser. Vol. 461, Astronomical Data Analysis Software and Systems XXI. Astron. Soc. Pac., San Francisco, p. 561
  15. Razavian A. S., Azizpour H., Sullivan J., Carlsson S., 2014, in Jose M. A., YannL.-C., Fatih P., Yi L., eds, Computer Vision and Pattern Recognition Workshops (CVPRW), IEEE Conference on Columbus, OH, p. 512
  16. Sifre L., Mallat S., 2013, in Gerard M., Ramin Z., eds, Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination. IEEE, New York, p. 1233
  17. Simonyan K., Zisserman A., 2015, in Yoshua B., Yann L.-C., eds, International Conference on Learning Representations. San Diego, CA
  18. Sutskever I., Martens J., Dahl G., Hinton G., 2013, in Sanjoy D., David M., eds, Proc. 30th Int. Conf. on Machine Learning (ICML-13), On the Importance of Initialization and Momentum in Deep Learning. Journal of Machine Learning Research, jmlr.org, p. 1139
  19. Szegedy C. et al., 2014, preprint (arXiv:1409.4842) · arXiv
  20. van der Walt S., Sch¨ onberger J. L., Nunez-Iglesias J., Boulogne F., Warner J. D., Yager N., Gouillart E., Yu T., 2014, Technical Report, scikit-image: Image Processing in Python. PeerJ 2:e453, available at: https://dx.doi.org/10.7717/peerj.453 · DOI

Cited by

Sorted by citations

Related

Authors
Dieleman, S., Willett, K. W., & Dambre, J.
Affiliations
  • Ghent University (BE)
  • University of Minnesota (US)
Corresponding author
  • Dieleman, Sander
  • Willett, Kyle W.
ORCID
Venue
Monthly Notices of the Royal Astronomical Society
Publisher
Oxford University Press (OUP)
Published
2015-04-25
Volume
450
Issue
2
Pages
1441-1459
ISSN
  • 0035-8711 (ISSN-L)
  • 1365-2966
DOI
10.1093/mnras/stv632
OpenAlex
W2044738244
Cited by
781
References
50
Citations by year
2026: 38 · 2025: 63 · 2024: 69 · 2023: 85 · 2022: 86 · 2021: 94 · 2020: 84 · 2019: 106 · 2018: 71 · 2017: 42 · 2016: 35 · 2015: 8
FWCI
29.59
Type
journal article
Language
en
Open access
Locations
  • Monthly Notices of the Royal Astronomical Society (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Ghent University Academic Bibliography (Ghent University) (submittedVersion)
  • HighWire Press Open Archive (submittedVersion)
  • arXiv (Cornell University)
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
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Biophysics › Cell Image Analysis Techniques
Keywords
galaxy morphology classification, rotational symmetry, translation invariance, Galaxy Zoo, automated image classification, galaxy formation and evolution, LSST

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