Semi-supervised Source Detection in Astronomical Images: New Benchmark and Strong Baseline
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 45 references that are in the map. First posted on arXiv 8 Jun 2026.
Builds on
22 of 45 references.
References · 22
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Feature Pyramid Networks for Object Detectioncited by 5,036
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
- 2015Fast R-CNNcited by 2,933
- 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
- 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
- 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
- 2021Oriented R-CNN for Object Detectioncited by 231
- 2021Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detectioncited by 49
- 2020Improving Object Detection with Selective Self-supervised Self-trainingcited by 35
- 2022Dense Learning based Semi-Supervised Object Detectioncited by 32
- 2020Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detectioncited by 29
10 more
- 2020Solving Missing-Annotation Object Detection with Background Recalibration Losscited by 27
- 2019Morpheus: A Deep Learning Framework For Pixel-Level Analysis of Astronomical Image Datacited by 15
- 2022SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Miningcited by 14
- 2020Temporal Self-Ensembling Teacher for Semi-Supervised Object Detectioncited by 12
- 2024Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detectioncited by 11
- 2020Semi-Supervised Object Detection with Sparsely Annotated Datasetcited by 10
- 2023Calibrated Teacher for Sparsely Annotated Object Detectioncited by 10
- 2018Stellar Cluster Detection using GMM with Deep Variational Autoencodercited by 2
- 2024Not Just Object, But State: Compositional Incremental Learning without Forgettingcited by 2
- 2024Panoptic Segmentation of Galactic Structures in LSB Imagescited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.