RECORD
DenseLens -- Using DenseNet ensembles and information criteria for finding and rank-ordering strong gravitational lenses,
Astrophysics of Galaxies · Submitted 14 Nov 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Thus, we recommend DenseNets for future missions involving large data sets, such as Euclid, where low false positive rates play a key role in the automated follow-up and analysis of large numbers of strong gravitational lens candidates when human vetting is no longer feasible
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Convolutional neural networks (CNNs) are the state-of-the-art technique for identifying strong gravitational lenses. Although they are highly successful in recovering genuine lens systems with a high true-positive rate, the unbalanced nature of the data set (lens systems are rare), still leads to a high false positive rate. For these techniques to be successful in upcoming surveys (e.g. with Euclid) most emphasis should be set on reducing false positives, rather than on reducing false negatives. In this paper, we introduce densely connected neural networks (DenseNets) as the CNN architecture in a new pipeline-ensemble model containing an ensemble of classification CNNs and regression CNNs to classify and rank-order lenses, respectively. We show that DenseNets achieve comparable true positive rates but considerably lower false positive rates (when compared to residual networks; ResNets). Thus, we recommend DenseNets for future missions involving large data sets, such as Euclid, where low false positive rates play a key role in the automated follow-up and analysis of large numbers of strong gravitational lens candidates when human vetting is no longer feasible
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Convolutional neural networks (CNNs) are the state-of-the-art technique for identifying strong gravitational lenses. | background 1.00 | 0.04 | 0.03 | asserted 1.00 |
| s1 | Although they are highly successful in recovering genuine lens systems with a high true-positive rate, the unbalanced nature of the data set (lens systems are rare), still leads to a high false positive rate. | background 0.86 | 0.13 | 0.03 | asserted 1.00 |
| s2 | For these techniques to be successful in upcoming surveys (e.g. with Euclid) most emphasis should be set on reducing false positives, rather than on reducing false negatives. | background 0.63 | 0.06 | 0.12 | asserted 0.84 |
| s3 | In this paper, we introduce densely connected neural networks (DenseNets) as the CNN architecture in a new pipeline-ensemble model containing an ensemble of classification CNNs and regression CNNs to classify and rank-order lenses, respectively. | contribution 0.54 | 0.86 | 0.08 | asserted 0.99 |
| s4 | We show that DenseNets achieve comparable true positive rates but considerably lower false positive rates (when compared to residual networks; ResNets). | result 1.00 | 0.95 | 0.35 | asserted 1.00 |
| s5 | Thus, we recommend DenseNets for future missions involving large data sets, such as Euclid, where low false positive rates play a key role in the automated follow-up and analysis of large numbers of strong gravitational lens candidates when human vetting is no longer feasible | future work 0.95 | 0.30 | 0.81 | asserted 0.80 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Convolutional neural networks (CNNs) are the state-of-the-art technique for identifying strong gravitational lenses. Although they are highly successful in recovering genuine lens systems with a high true-positive rate, the unbalanced nature of the data set (lens systems are rare), still leads to a high false positive rate. For these techniques to be successful in upcoming surveys (e.g. with Euclid) most emphasis should be set on reducing false positives, rather than on reducing false negatives. In this paper, we introduce densely connected neural networks (DenseNets) as the CNN architecture in a new pipeline-ensemble model containing an ensemble of classification CNNs and regression CNNs to classify and rank-order lenses, respectively. We show that DenseNets achieve comparable true positive rates but considerably lower false positive rates (when compared to residual networks; ResNets). Thus, we recommend DenseNets for future missions involving large data sets, such as Euclid, where low false positive rates play a key role in the automated follow-up and analysis of large numbers of strong gravitational lens candidates when human vetting is no longer feasible
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.