Mining for Strong Gravitational Lenses with Self-supervised Learning
Open accessAbstract
We employ self-supervised representation learning to distill information from 76 million galaxy images from the Dark Energy Spectroscopic Instrument Legacy Imaging Surveys’ Data Release 9. Targeting the identification of new strong gravitational lens candidates, we first create a rapid similarity search tool to discover new strong lenses given only a single labeled example. We then show how training a simple linear classifier on the self-supervised representations, requiring only a few minutes on a CPU, can automatically classify strong lenses with great efficiency. We present 1192 new strong lens candidates that we identified through a brief visual identification campaign and release an interactive web-based similarity search tool and the top network predictions to facilitate crowd-sourcing rapid discovery of additional strong gravitational lenses and other rare objects: github.com/georgestein/ssl-legacysurvey.
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.
Integrity signals
Registry
Cites
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.
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?
Once the encoder section of a self-supervised model has been trained, one can conduct a simple similarity search to find objects of interest, or apply a linear classifier directly onto the encoder's outputs to separate the data into a variety of classes.
“Hayat et al. (2021) and Stein et al. (2022) show that once the encoder section of a self-supervised model has been trained one can conduct a simple similarity search to find objects of interest, or apply a linear classifier directly onto the encoder's outputs to separate the data into a variety of classes.”
From Detecting galaxy tidal features using self-supervised representation learning (2024) · cites this paper as Stein et al. 2022
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
Schlegel, D. J., Finkbeiner, D. P., & Davis, M. (1998) · The Astrophysical Journal · doi:10.1086/305772 · Cited by 15,126 · cited 1× · see citing works
“We first deredden the image according to its tabulated E(B− V ) value (Schlegel et al. 1998), simulating a view of the galaxy with no foreground dust.”
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857 · see citing works
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jégou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · arXiv · Cited by 5,932
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. A., Guo, Z. D., Azar, M. G., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.07733 · Cited by 3,846 · see citing works
Improved Baselines with Momentum Contrastive LearningPreprint
Chen, X., Fan, H., Girshick, R., & He, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.04297 · Cited by 2,579 · see citing works
Adversarial Feature LearningPreprint
Donahue, J., Krähenbühl, P., & Darrell, T. (2016) · International Conference on Learning Representations · doi:10.48550/arxiv.1605.09782 · Cited by 1,982 · see citing works
Overview of the DESI Legacy Imaging Surveys
Dey, A., Schlegel, D. J., Lang, D., Blum, R., Burleigh, K., Fan, X., Findlay, J. R., Finkbeiner, D. P., Herrera, D., Juneau, S., et al. (2019) · The Astronomical Journal · doi:10.3847/1538-3881/ab089d · Cited by 1,881 · see citing works
Lintott, C. J., Schawinski, K., Slosar, A., Land, K., Bamford, S., Thomas, D., Raddick, M. J., Nichol, R. C., Szalay, A., Andreescu, D., et al. (2008) · Monthly Notices of the Royal Astronomical Society · doi:10.1111/j.1365-2966.2008.13689.x · Cited by 1,488 · see citing works
Big Self-Supervised Models are Strong Semi-Supervised LearnersPreprint
Chen, T., Kornblith, S., Swersky, K., Norouzi, M., & Hinton, G. E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.10029 · Cited by 1,480 · see citing works
Overview of the DESI Legacy Imaging SurveysPreprint
Dey, A. T., Schlegel, D. J., Lang, D., Blum, R., Burleigh, K., Fan, X., Findlay, J. R., Finkbeiner, D. P., Herrera, D., Juneau, S., et al. (2018) · HAL · Cited by 1,221 · see citing works
Wong, K. C., Suyu, S. H., Chen, G. C.-F., Rusu, C. E., Millon, M., Sluse, D., Bonvin, V., Fassnacht, C. D., Taubenberger, S., Auger, M. W., et al. (2019) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz3094 · Cited by 1,178 · see citing works
Willett, K. W., Lintott, C. J., Bamford, S. P., Masters, K. L., Simmons, B. D., Casteels, K. R. V., Edmondson, E. M., Fortson, L. F., Kaviraj, S., Keel, W. C., et al. (2013) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stt1458 · Cited by 659 · see citing works
Turner, E. L., Ostriker, J. P., & R., I. G. J. (1984) · The Astrophysical Journal · doi:10.1086/162379 · Cited by 638 · see citing works
Treu, T. (2010) · Annual Review of Astronomy and Astrophysics · doi:10.1146/annurev-astro-081309-130924 · Cited by 467 · see citing works
Large Scale Adversarial Representation LearningPreprint
Donahue, J., & Simonyan, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.02544 · Cited by 398 · see citing works
THE POPULATION OF GALAXY–GALAXY STRONG LENSES IN FORTHCOMING OPTICAL IMAGING SURVEYS
Collett, T. E. (2015) · The Astrophysical Journal · doi:10.1088/0004-637x/811/1/20 · Cited by 354 · see citing works
CMU DeepLens: deep learning for automatic image-based galaxy–galaxy strong lens finding
Lanusse, F., Ma, Q., Li, N., Collett, T. E., Li, C.-L., Ravanbakhsh, S., Mandelbaum, R., & Póczos, B. (2018) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stx1665 · Cited by 191 · see citing works
Finding strong gravitational lenses in the Kilo Degree Survey with Convolutional Neural Networks
Petrillo, C. E., Tortora, C., Chatterjee, S., Vernardos, G., Koopmans, L. V. E., Kleijn, G. V., Napolitano, N. R., Covone, G., Schneider, P., Grado, A., et al. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stx2052 · Cited by 189 · see citing works
The clustering of DESI-like luminous red galaxies using photometric redshifts
Zhou, R., Newman, J. A., Mao, Y.-Y., Meisner, A., Moustakas, J., Myers, A. D., Prakash, A., Zentner, A. R., Brooks, D., Duan, Y., et al. (2020) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staa3764 · Cited by 186 · see citing works
Galaxy Zoo: probabilistic morphology through Bayesian CNNs and active learning
Walmsley, M., Smith, L., Lintott, C., Gal, Y., Bamford, S., Dickinson, H., Fortson, L., Kruk, S., Masters, K., Scarlata, C., et al. (2020) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz2816 · Cited by 160 · see citing works
The strong gravitational lens finding challenge
Metcalf, R. B., Meneghetti, M., Avestruz, C., Bellagamba, F., Bom, C. R., Bertin, E., Cabanac, R., Courbin, F., Davies, A., Decencière, E., et al. (2019) · Astronomy & Astrophysics · doi:10.1051/0004-6361/201832797 · Cited by 152 · see citing works
Self-supervised Pretraining of Visual Features in the Wild
Goyal, P., Caron, M., Lefaudeux, B., Xu, M., Wang, P., Pai, V., Singh, M., Liptchinsky, V., Misra, I., Joulin, A., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.01988 · Cited by 141 · see citing works
Finding strong lenses in CFHTLS using convolutional neural networks
Jacobs, C., Glazebrook, K., Collett, T., More, A., & McCarthy, C. (2017) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stx1492 · Cited by 133 · cited 4× · see citing works
“In recent years, the search for strong lenses has been dominated by the use of CNNs trained in a standard supervised learning setup (e.g., Jacobs et al. 2017, 2019a, 2019b; Petrillo et al. 2017, 2019; Lanusse et al. 2018; Cañameras et al. 2020, 2021; He et al. 2020; Huang et al. 2020, 2021; Li et…”
BackgroundMethodInfluentialGilman, D., Birrer, S., Treu, T., Nierenberg, A. M., & Benson, A. (2019) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz1593 · Cited by 126 · see citing works
Sonnenfeld, A., Chan, J. H. H., Shu, Y., More, A., Oguri, M., Suyu, S. H., Wong, K. C., Lee, C.-H., Coupon, J., Yonehara, A., et al. (2017) · Publications of the Astronomical Society of Japan · doi:10.1093/pasj/psx062 · Cited by 108 · see citing works
Petrillo, C. E., Tortora, C., Vernardos, G., Koopmans, L. V. E., Kleijn, G. V., Bilicki, M., Napolitano, N. R., Chatterjee, S., Covone, G., Dvornik, A., et al. (2019) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz189 · Cited by 108 · see citing works
Finding Strong Gravitational Lenses in the DESI DECam Legacy Survey
Huang, X., Storfer, C., Ravi, V., Pilon, A., Domingo, M., Schlegel, D. J., Bailey, S., Dey, A. T., Gupta, R. R., Herrera, D., et al. (2020) · The Astrophysical Journal · doi:10.3847/1538-4357/ab7ffb · Cited by 104 · see citing works
Finding high-redshift strong lenses in DES using convolutional neural networks
Jacobs, C., Collett, T. E., Glazebrook, K., McCarthy, C. D., Qin, A. K., Abbott, T. M. C., Abdalla, F. B., Annis, J. T., Avila, S., Bechtol, K., et al. (2019) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stz272 · Cited by 103 · see citing works
Cañameras, R., Schuldt, S., Suyu, S. H., Taubenberger, S., Meinhardt, T., Leal-Taixé, L., Lemon, C., Rojas, K., & Savary, E. (2020) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202038219 · Cited by 85 · see citing works
Identifying strong lenses with unsupervised machine learning using convolutional autoencoder
Cheng, T.-Y., Li, N., Conselice, C. J., Aragón‐Salamanca, A., Dye, S., & Metcalf, R. B. (2020) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staa1015 · Cited by 80 · see citing works
LensFlow: A Convolutional Neural Network in Search of Strong Gravitational Lenses
Pourrahmani, M., Nayyeri, H., & Cooray, A. R. (2018) · The Astrophysical Journal · doi:10.3847/1538-4357/aaae6a · Cited by 79 · see citing works
New High-quality Strong Lens Candidates with Deep Learning in the Kilo-Degree Survey
Li, R., Napolitano, N. R., Tortora, C., Spiniello, C., Koopmans, L. V. E., Huang, Z., Roy, N., Vernardos, G., Chatterjee, S., Giblin, B., et al. (2020) · The Astrophysical Journal · doi:10.3847/1538-4357/ab9dfa · Cited by 79 · see citing works
Self-supervised Representation Learning for Astronomical Images
Hayat, M. A., Stein, G., Harrington, P., Lukić, Z., & Mustafa, M. (2021) · The Astrophysical Journal Letters · doi:10.3847/2041-8213/abf2c7 · Cited by 79 · cited 10× · see citing works
“…orientation of the galaxies, the number of sources, the clustering, and the color, while removing the noise and symmetries described by the data augmentations (for a visualization of how galaxy properties are organized in the representation space of a self-supervised model, see Hayat et al. 2021).”
BackgroundMethodInfluentialSelf-citationSonnenfeld, A., Chan, J., Shu, Y., More, A., Oguri, M., Suyu, S. H., Wong, K., Lee, C., Coupon, J., Yonehara, A., et al. (2018) · Max Planck Digital Library · Cited by 78 · see citing works
Diehl, H. T., Buckley‐Geer, E., Lindgren, K. A., Nord, B., Gaitsch, H., Gaitsch, S., Lin, H., Allam, S., Collett, T. E., Furlanetto, C., et al. (2017) · The Astrophysical Journal Supplement Series · doi:10.3847/1538-4365/aa8667 · Cited by 77 · see citing works
Survey of gravitationally-lensed objects in HSC imaging (SuGOHI)
Sonnenfeld, A., Jaelani, A. T., Chan, J. H. H., More, A., Suyu, S. H., Wong, K. C., Oguri, M., & Lee, C. (2019) · Astronomy and Astrophysics · doi:10.1051/0004-6361/201935743 · Cited by 70 · see citing works
Wong, K. C., Sonnenfeld, A., Chan, J. H. H., Rusu, C. E., Tanaka, M., Jaelani, A. T., Lee, C., More, A., Oguri, M., Suyu, S. H., et al. (2018) · The Astrophysical Journal · doi:10.3847/1538-4357/aae381 · Cited by 69 · see citing works
Sonnenfeld, A., Verma, A., More, A., Baeten, E., Macmillan, C., Wong, K. C., Chan, J. H. H., Jaelani, A. T., Lee, C.-H., Oguri, M., et al. (2020) · Astronomy & Astrophysics · doi:10.1051/0004-6361/202038067 · Cited by 67 · see citing works
Discovering New Strong Gravitational Lenses in the DESI Legacy Imaging Surveys
Huang, X., Storfer, C., Gu, A., Ravi, V., Pilon, A., Sheu, W., Venguswamy, R., Banka, S., Dey, A., Landriau, M., et al. (2020) · Astrophysical Journal · doi:10.3847/1538-4357/abd62b · Cited by 60 · see citing works
Search of strong lens systems in the Dark Energy Survey using convolutional neural networks
Rojas, K., Savary, É., Clément, B., Maus, M., Courbin, F., Lemon, C., Chan, J. H. H., Vernardos, G., Joseph, R., Cañameras, R., et al. (2022) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202142119 · Cited by 60 · see citing works
High-quality Strong Lens Candidates in the Final Kilo-Degree Survey Footprint
Li, R., Napolitano, N. R., Spiniello, C., Tortora, C., Kuijken, K. H., Koopmans, L. V. E., Schneider, P., Getman, F. I., Xie, L., Long, L., et al. (2021) · The Astrophysical Journal · doi:10.3847/1538-4357/ac2df0 · Cited by 59 · see citing works
Cañameras, R., Schuldt, S., Shu, Y., Suyu, S. H., Taubenberger, S., Meinhardt, T., Leal-Taixé, L., Chao, D. C.-Y., Inoue, K. T., Jaelani, A. T., et al. (2021) · Astronomy and Astrophysics · doi:10.1051/0004-6361/202141758 · Cited by 55 · see citing works
Jaelani, A. T., More, A., Oguri, M., Sonnenfeld, A., Suyu, S. H., Rusu, C. E., Wong, K. C., Chan, J. H. H., Kayo, I., Lee, C., et al. (2020) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staa1062 · Cited by 51 · see citing works
Survey of Gravitationally lensed Objects in HSC Imaging (SuGOHI)
Chan, J. H. H., Suyu, S. H., Sonnenfeld, A., Jaelani, A. T., More, A., Yonehara, A., Kubota, Y., Coupon, J., Lee, C., Oguri, M., et al. (2020) · Astronomy and Astrophysics · doi:10.1051/0004-6361/201937030 · Cited by 43 · see citing works
He, Z., Er, X., Long, Q., Liu, D., Liu, X., Li, Z., Liu, Y., Deng, W., & Fan, Z. (2020) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/staa1917 · Cited by 42 · see citing works
Caputi, K. I., Caminha, G. B., Fujimoto, S., et al. (2021) · The Astrophysical Journal · doi:10.3847/1538-4357/abd4d0 · Cited by 39 · see citing works
Pushing automated morphological classifications to their limits with the Dark Energy Survey
Vega-Ferrero, J., Sánchez, H. D., Bernardi, M., M. Huertas-Company, Morgan, R., Margalef, B., Aguena, M., Allam, S., Annis, J., Ávila, S., et al. (2020) · Monthly notices of the Royal Astronomical Society · doi:10.1093/mnras/stab594 · Cited by 22 · see citing works
VLT/MAGELLAN SPECTROSCOPY OF 29 STRONG LENSING SELECTED GALAXY CLUSTERS
Carrasco, M., Barrientos, L. F., Anguita, T., et al. (2017) · The Astrophysical Journal · doi:10.3847/1538-4357/834/2/210 · Cited by 18 · see citing works
Unsupervised Learning of Visual Representations by Solving Jigsaw PuzzlesPreprint
Noroozi, M., & Favaro, P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.09246 · Cited by 17 · see citing works
VLT/Magellan spectroscopy of 29 strong lensing selected galaxy clusters
Carrasco, M., Barrientos, L. F., Anguita, T., et al. (2017) · Max Planck Institute for Plasma Physics · Cited by 13 · see citing works
georgestein/ml-in-cosmology: Machine learning in cosmology
Stein, G. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.4024768 · Cited by 8 · see citing works
Self-citationGentile, F., Tortora, C., Covone, G., Koopmans, L. V. E., Spiniello, C., Fan, Z., Li, R., Liu, D., Napolitano, N. R., Vaccari, M., et al. (2021) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stab3386 · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 8
- He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. 2020, in Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (Piscataway, NJ: IEEE), 9729
- Hendrycks, D., Mazeika, M., Kadavath, S., & Song, D. 2019, arXiv:1906. 12340
- Jacobs, C., Collett, T., Glazebrook, K., et al. 2019b, ApJS, 243, 17 · DOI
- Paszke, A., Gross, S., Massa, F., et al. 2019, in Advances in Neural Information Processing Systems 32, ed. H. Wallach et al. (Red Hook, NY: Curran Associates Inc.), 8024
- Reed, C. J., Metzger, S., Srinivas, A., Darrell, T., & Keutzer, K. 2020, arXiv:2009.07724 · arXiv
- Rojas, K., Savary, E., Clément, B., et al. 2021, arXiv:2109.00014 · arXiv
- Stein, G., Harrington, P., Blaum, J., Medan, T., & Lukic, Z. 2021, arXiv:2110. 13151
- Zhai, X., Oliver, A., Kolesnikov, A., & Beyer, L. 2019, in Proc. IEEE/CVF Int. Conf. on Computer Vision (ICCV) (Piscataway, NJ: IEEE), 1476
Cited by
Sorted by citations
Pearce-Casey, R., Nagam, B. C., Wilde, J., Busillo, V., Ulivi, L., Andika, I. T., Manjón-García, A., Leuzzi, L., Matavulj, P., Serjeant, S., et al. (2025) · Astronomy & Astrophysics · doi:10.1051/0004-6361/202453152 · Cited by 18 · see citing works
Cañameras, R., Schuldt, S., Shu, Y., Suyu, S. H., Taubenberger, S., Andika, I. T., Bag, S., Inoue, K. T., Jaelani, A. T., Leal-Taixé, L., et al. (2024) · Astronomy & Astrophysics · doi:10.1051/0004-6361/202347072 · Cited by 19 · see citing works
Detecting galaxy tidal features using self-supervised representation learning
Desmons, A., Brough, S., & Lanusse, F. (2024) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stae1402 · Cited by 15 · see citing works
Self-supervised similarity search for large scientific datasets
Stein, G., Harrington, P., Blaum, J., Medan, T., & Lukic, Z. (2021) · arXiv · doi:10.48550/arxiv.2110.13151 · Cited by 13 · see citing works
Self-citation
- Authors
- Stein, G., Blaum, J., Harrington, P., Medan, T., & Lukić, Z.
- Affiliations
- Lawrence Berkeley National Laboratory (US)
- Corresponding author
- Stein, George
- Blaum, Jacqueline
- Harrington, Peter
- Medan, Tomislav
- Lukić, Zarija
- Venue
- The Astrophysical Journal
- Publisher
- American Astronomical Society
- Published
- 2022-06-01
- Volume
- 932
- Issue
- 2
- Pages
- 107
- ISSN
- 0004-637X (ISSN-L)
- 1538-4357
- OpenAlex
- W3202552603
- Cited by
- 52
- References
- 53
- Citations by year
- 2026: 8 · 2025: 15 · 2024: 13 · 2023: 11 · 2022: 4 · 2021: 1
- FWCI
- 4.30
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- The Astrophysical Journal (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- U.S. Department of Energy (DESC0007914)
- Topics
- Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Galaxies: Formation, Evolution, Phenomena
- Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Astrophysical Phenomena and Observations
- Physical Sciences › Physics and Astronomy › Astronomy and Astrophysics › Gamma-ray bursts and supernovae
- Keywords
- strong gravitational lenses, self-supervised representation learning, similarity search, linear classifiers, DESI Legacy Imaging Surveys, galaxy images, crowdsourcing, rare object detection
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
