Deep convolutional neural networks as strong gravitational lens detectors
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Context.Future large-scale surveys with high-resolution imaging will provide us with approximately 10 5 new strong galaxy-scale lenses. These strong-lensing systems will be contained in large data amounts, however, which are beyond the capacity of human experts to visually classify in an unbiased way.Aims.We present a new strong gravitational lens finder based on convolutional neural networks (CNNs). The method was applied to the strong-lensing challenge organized by the Bologna Lens Factory. It achieved first and third place, respectively, on the space-based data set and the ground-based data set. The goal was to find a fully automated lens finder for ground-based and space-based surveys that minimizes human inspection. Methods.We compared the results of our CNN architecture and three new variations (“invariant” “views” and “residual”) on the simulated data of the challenge. Each method was trained separately five times on 17 000 simulated images, cross-validated using 3000 images, and then applied to a test set with 100 000 images. We used two different metrics for evaluation, the area under the receiver operating characteristic curve (AUC) score, and the recall with no false positive (Recall 0FP). Results.For ground-based data, our best method achieved an AUC score of 0.977 and a Recall 0FP of 0.50. For space-based data, our best method achieved an AUC score of 0.940 and a Recall 0FP of 0.32. Adding dihedral invariance to the CNN architecture diminished the overall score on space-based data, but achieved a higher no-contamination recall. We found that using committees of five CNNs produced the best recall at zero contamination and consistently scored better AUC than a single CNN. Conclusions.We found that for every variation of our CNN lensfinder, we achieved AUC scores close to 1 within 6%. A deeper network did not outperform simpler CNN models either. This indicates that more complex networks are not needed to model the simulated lenses. To verify this, more realistic lens simulations with more lens-like structures (spiral galaxies or ring galaxies) are needed to compare the performance of deeper and shallower networks.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Rotation-invariant convolutional neural networks for galaxy morphology prediction
Dieleman, S., Willett, K. W., & Dambre, J. (2015) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stv632 · Cited by 781
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 · cited 1×
“In the GGSLC challenge, Francois Lanusse’s deep lens classifier (Lanusse et al. 2018) used residual learning to create a 46-layer deep CNN that won the ground part of the challenge.”
MethodFinding 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 2×
“Recently, Petrillo et al. (2017) and Jacobs et al. (2017) started using convolutional neural networks (CNNs) for lens detection.”
MethodMore, A., Verma, A., Marshall, P. J., More, S., Baeten, E., Wilcox, J., Macmillan, C., Cornen, C., Kapadia, A., Parrish, M., et al. (2016) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stv1965 · Cited by 116 · cited 1×
“They found 29 promising new lens candidates in the survey (More et al. 2016), but this method will likely be too slow and too much subject to human error for future data sets.”
Background
Cited by
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
Self-citationThe Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys
Huertas-Company, M., & Lanusse, F. (2023) · Publications of the Astronomical Society of Australia · doi:10.1017/pasa.2022.55 · Cited by 102
“…the advent of deep learning is the detection of strong gravitational lenses (e.g. Jacobs et al., 2017; Petrillo et al., 2017; Lanusse et al., 2018; Davies et al., 2019; Schaefer et al., 2018; Metcalf et al., 2019; Petrillo et al., 2019; Jacobs et al., 2019; Li et al., 2020b; Huang et al., 2020).”
BackgroundPearson, J., Maresca, J., Li, N., & Dye, S. (2021) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stab1547 · Cited by 31
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
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
Metadata
- Authors
- Schaefer, C., Geiger, M., Kuntzer, T., & Kneib, J.-P.
- Venue
- Astronomy & Astrophysics
- Publisher
- EDP Sciences
- Published
- 2018-03
- Volume
- 611
- Pages
- A2
- ISSN
- 0004-6361 (ISSN-L)
- 1432-0746
- OpenAlex
- W2618904690
- Cited by
- 84
- References
- 7
- FWCI
- 3.51
- Type
- journal article
- Language
- en
- Open access
- bronze
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Deep convolutional neural networks as strong gravitational lens detectors. https://app.cochat.ai/papers/10.1051/0004-6361/201731201
- The paper
- Schaefer, C., Geiger, M., Kuntzer, T., & Kneib, J.-P. (2018). Deep convolutional neural networks as strong gravitational lens detectors. Astronomy & Astrophysics. https://doi.org/10.1051/0004-6361/201731201
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.