Quasars experiencing strong lensing offer unique viewpoints on subjects related to the cosmic expansion rate, the dark matter profile within the foreground deflectors, and the quasar host galaxies. Unfortunately, identifying them in astronomical images is challenging since they are overwhelmed by the abundance of non-lenses. To address this, we have developed a novel approach by ensembling cutting-edge convolutional networks (CNNs) -- for instance, ResNet, Inception, NASNet, MobileNet, EfficientNet, and RegNet -- along with vision transformers (ViTs) trained on realistic galaxy-quasar lens simulations based on the Hyper Suprime-Cam (HSC) multiband images. While the individual model exhibits remarkable performance when evaluated against the test dataset, achieving an area under the receiver operating characteristic curve of $>$97.3% and a median false positive rate of 3.6%, it struggles to generalize in real data, indicated by numerous spurious sources picked by each classifier. A significant improvement is achieved by averaging these CNNs and ViTs, resulting in the impurities being downsized by factors up to 50. Subsequently, combining the HSC images with the UKIRT, VISTA, and unWISE data, we retrieve approximately 60 million sources as parent samples and reduce this to 892,609 after employing a photometry preselection to discover $z>1.5$ lensed quasars with Einstein radii of $\theta_\mathrm{E}<5$ arcsec. Afterward, the ensemble classifier indicates 3080 sources with a high probability of being lenses, for which we visually inspect, yielding 210 prevailing candidates awaiting spectroscopic confirmation. These outcomes suggest that automated deep learning pipelines hold great potential in effectively detecting strong lenses in vast datasets with minimal manual visual inspection involved.

翻译：遭受强引力透镜效应的类星体为研究宇宙膨胀速率、前景偏转体中的暗物质分布以及类星体宿主星系提供了独特视角。然而，在天文图像中识别它们极具挑战性，因为非透镜天体的数量远多于透镜天体。为解决这一问题，我们开发了一种新方法，通过集成前沿卷积神经网络（CNN）——例如ResNet、Inception、NASNet、MobileNet、EfficientNet和RegNet——以及基于Hyper Suprime-Cam（HSC）多波段图像训练的星系-类星体透镜模拟数据上的视觉Transformer（ViT）来实现。尽管单个模型在测试数据集上表现出色，接收者操作特征曲线下面积达>97.3%，中位假阳性率为3.6%，但在实际数据中泛化能力不足，表现为每个分类器检测到大量虚假源。通过平均这些CNN和ViT，我们实现了显著改进，杂质减少幅度高达50倍。随后，结合HSC图像与UKIRT、VISTA和unWISE数据，我们获取了约6000万个源作为母样本，并通过光度预筛选将样本缩减至892,609个，以发现红移$z>1.5$且爱因斯坦半径$\theta_\mathrm{E}<5$角秒的透镜类星体。之后，集成分类器指出3080个具有高透镜概率的源，我们对这些源进行目视检查，得到210个有望候选体，等待光谱确认。这些结果表明，自动化深度学习管道在从海量数据中有效检测强透镜体方面具有巨大潜力，且仅需极少量的人工目视检查。