Euclid Quick Data Release (Q1). AstroVink: A vision transformer approach to find strong gravitational lens systems

TL;DR

AstroVink, a vision transformer model based on DINOv2, effectively identifies strong gravitational lens candidates in Euclid data, reducing manual inspection efforts and improving detection accuracy.

Contribution

The paper introduces AstroVink, a novel vision transformer approach fine-tuned for Euclid lens detection, demonstrating improved performance with real data and negative examples.

Findings

Recovered all 110 known lens systems in the test set.

Reduced inspection effort to approximately one lens per 4.5 objects.

Identified 34 new high-confidence lens candidates in Euclid data.

Abstract

We present AstroVink, a vision transformer classifier designed for automated identification of strong lens candidates in Euclid imaging. We build upon the DINOv2 encoder, fine tuned to distinguish between lens and non-lens galaxies. Our base model, trained on simulated strong lens systems and labelled non lenses, recovers 88 of the 110 lens candidates within the top 500 ranked candidates, corresponding to an inspection efficiency of one lens per 5.7 inspected objects in our test set. After the Q1 data release, which yielded about 500 lens candidates, we retrained the model using high confidence lens candidates and new negatives, initially flagged as potential lenses by other classifiers but rejected during visual inspection. The retrained network further improves performance, achieving recovery of all 110 systems within the same ranking and reducing the inspection effort to one lens per 4.5 inspected objects, demonstrating that incorporating real examples significantly enhances model generalisation. An analysis of training subsets revealed that the inclusion of realistic negative examples played a key role in this improvement. Finally, we applied the retrained model to the Q1 original selection of 1.08M targets, followed by a new round of Space Warps citizen science inspection and expert vetting, where we identified a total of eight Grade A and 26 Grade B new lens candidates. These results demonstrate that transformer based architectures can recover strong lens candidates with high efficiency in real Euclid data, while substantially reducing the number of candidates requiring visual inspection.