Semi-supervised Source Detection in Astronomical Images: New Benchmark and Strong Baseline
2026-06-08 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on improving how we find stars and other space objects in big, crowded telescope images, which is hard because these objects can be very small and dim. They created a large dataset called LAMOST-DET with lots of labeled images to help with this problem. They also designed a new method called Nova Teacher that learns to detect these objects even when it has only a few examples to learn from. Their method works better than previous ones and also does well on regular photos, showing it can be used in different situations.
source detectionastronomical imagessemi-supervised learningpoint spread functionsignal-to-noise ratiodataset benchmarkpseudo-supervisionobject detectorsmean average precisiondual-teacher paradigm
Authors
Longhan Feng, Zihuang Cao, Ali Luo, Yuanhao Guo, Shuilian Yao, Yixin Guo, Qi Jia, Yu Liu
Abstract
Source detection in modern observational astronomy is a cornerstone for localizing and identifying stellar sources accurately. It is crucial for studies such as stellar population synthesis and cosmological parameter estimation. However, the characteristics of astronomical images, including high density, the effect of point spread functions and low signal-to-noise ratios, significantly challenge the latest advanced object detectors. Besides, fully-supervised detection methods are hardly practical, due to the significant difficulty in annotating dense, small, and faint sources in astronomical images. To tackle the scarcity of astronomical datasets, we introduce a new comprehensive benchmark (LAMOST-DET), comprising 18,400 astronomical images and 728,898 source instances. Upon the dataset, we further devise a novel semi-supervised learning framework coined Nova Teacher, capable of detecting dense sources effectively given sparse annotations. It integrates source light enhancement module, confidence-guided pseudo-supervision, and cross-view complementary mining in a dual-teacher paradigm. Extensive experiments on LAMOST-DET show that, Nova Teacher consistently improves previous competitors by 4.04% and 5.22% mAP under two semi-supervised settings. Additionally, our method competes against other detectors on a natural image dataset, validating its generalization ability to various scenarios. The source code is available at https://github.com/AcWiz/NovaTeacher.