The promise of self-supervised and active learning for strong lens discovery: Astronomaly applied to KiDS
Year: 2026
Type: article
Abstract: ABSTRACT Strong gravitational lenses (SGLs) are rare systems whose discovery currently relies primarily on supervised machine learning methods trained on large simulated data sets. We present the first application of Astronomaly:Protege to SGL discovery, demonstrating that a human-in-the-loop active learning framework can efficiently identify lenses in large imaging surveys without the need for simulated training data. We consider a sample of 3.7 million bright galaxies from the Kilo-Degree Survey (KiDS) DR4. Feature representations are extracted using a convolutional neural network pre-trained on the ImageNet data set and subsequently fine-tuned on KiDS data using the self-supervised Bootstrap Your Own Latent (BYOL) framework. Within the embedding of these representations, the active learning loop ofAstronomaly iteratively selects the most informative systems for expert inspection. A total of 3000 objects are inspected across multiple rounds, yielding 34 high-quality (grade A/B) SGL candidates. On the basis that these systems occupy similar regions in the learned feature space, we expand this sample through nearest-neighbour similarity analysis. Including the active learning discoveries, we identify a total of 140 grade A/B candidates and more than 1000 additional lower-confidence systems (grade C). Among the A/B candidates, 81 are newly identified, while $\sim$22 per cent of previously known grade A/B KiDS lenses are recovered. These results demonstrate strong potential for next-generation surveys such as Euclid, Roman, and Rubin’s Legacy Survey of Space and Time. With approximately 60 per cent of the high-quality candidates newly reported, this approach complements supervised methods by reducing reliance on simulations and enabling the discovery of a diverse population of SGLs.
Language: English
Subfield: Astronomy and Astrophysics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,046
Funders: Neurosciences Research Foundation, National Research Foundation, University of Pretoria, Deutsche Forschungsgemeinschaft, Nederlandse Organisatie voor Wetenschappelijk Onderzoek, Università degli Studi di Padova, University of the Western Cape, Cape Peninsula University of Technology, University of Cape Town, Narodowa Agencja Wymiany Akademickiej, Nurses Organization of Veterans Affairs, H2020 European Research Council
Award: G9000373409
OpenAlex ID: W7204992760