Quasars experiencing strong lensing offer unique viewpoints on subjects like 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) -- i.e., 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 $>$97.4% and a median false positive rate of 3.1%, 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 40. 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 3991 sources with a high probability of being lenses, for which we visually inspect, yielding 161 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：强引力透镜化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主星系等课题提供了独特视角。然而，由于非透镜天体数量众多，在天文图像中识别它们极具挑战性。为解决这一问题，我们提出了一种新方法：集成前沿卷积神经网络（CNN）——包括ResNet、Inception、NASNet、MobileNet、EfficientNet和RegNet——以及视觉Transformer（ViT），这些模型基于超新星主焦点相机（HSC）多波段图像的真实星系-类星体透镜模拟进行训练。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（AUC）超过97.4%，中位假阳性率为3.1%，但它们在真实数据中泛化能力较差，每个分类器均检测出大量虚假源。通过对这些CNN和ViT进行平均，我们取得了显著改进，杂质数量最多减少了40倍。随后，结合HSC图像与UKIRT、VISTA及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其缩减至892,609个，以发现爱因斯坦半径θ_E<5角秒的红移z>1.5的双透镜类星体。此后，集成分类器识别出3991个高概率透镜源，经目视检查后得到161个候选目标，等待光谱确认。这些结果表明，自动化深度学习管道在处理大规模数据集中有效检测强透镜体方面具有巨大潜力，且所需人工目视检查最少。