# Finding Strong Gravitational Lenses Through Self-Attention

arXiv: https://arxiv.org/abs/2110.09202 · HTML: https://mlsanity.com/paper/2110.09202/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 18 Oct 2021.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [Exploring Self-attention for Image Recognition](https://mlsanity.com/paper/2004.13621/) (2020)
- [Relative Positional Encoding for Transformers with Linear Complexity](https://mlsanity.com/paper/2105.08399/) (2021)
- [Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification](https://mlsanity.com/paper/1801.09927/) (2018)
- [Explicitly Modeled Attention Maps for Image Classification](https://mlsanity.com/paper/2006.07872/) (2020)
- [A Comparative Study of Convolutional Neural Networks for the Detection of Strong Gravitational Lensing](https://mlsanity.com/paper/2106.01754/) (2021)

## Built on by (most cited first, 1 of 1)

- [Strong Gravitational Lensing Parameter Estimation with Vision Transformer](https://mlsanity.com/paper/2210.04143/) (2022)

## Abstract (arXiv)

The upcoming large scale surveys like LSST are expected to find approximately 105 strong gravitational lenses by analysing data of many orders of magnitude larger than those in contemporary astronomical surveys. In this case, non-automated techniques will be highly challenging and time-consuming, even if they are possible at all. We propose a new automated architecture based on the principle of self-attention to find strong gravitational lenses. The advantages of self-attention-based encoder models over convolution neural networks are investigated, and ways to optimise the outcome of encoder models are analysed. We constructed and trained 21 self-attention based encoder models and five convolution neural networks to identify gravitational lenses from the Bologna Lens Challenge. Each model was trained separately using 18,000 simulated images, cross-validated using 2,000 images, and then applied to a test set with 100,000 images. We used four different metrics for evaluation: classification accuracy, area under the receiver operating characteristic curve (AUROC), the TPR0 score and the TPR10 score. The performances of self-attention-based encoder models and CNNs participating in the challenge are compared. They were able to surpass the CNN models that participated in the Bologna Lens Challenge by a high margin for the TPR0 and TPR_10. Self-Attention based models have clear advantages compared to simpler CNNs. They have highly competing performance in comparison to the currently used residual neural networks. Compared to CNNs, self-attention based models can identify highly confident lensing candidates and will be able to filter out potential candidates from real data. Moreover, introducing the encoder layers can also tackle the over-fitting problem present in the CNNs by acting as effective filters.