Making Euclid VIS Imaging AI-Ready: A Scalable Pipeline for Morphology, Anomaly Detection, and Similarity Search
Abstract
The Euclid mission is delivering an unprecedented volume of high-resolution galaxy imaging, posing new challenges for standardized and reproducible reuse across morphological analyses. We present a scalable pipeline that converts released VIS cutouts into standardized 224×224 model inputs and uses a pretrained DINOv2 ViT-S/14 feature extractor to construct a 365,513-row, 384-dimensional cutout-and-embedding product from the Galaxy Zoo Euclid (Q1) catalogue. Initial production of the 365,513 released cutouts required approximately 48 hours, corresponding to an estimated end-to-end rate of $2.12$ cutouts s−1. The service supports batch task management, while persistent reuse of generated products avoids repeating mosaic extraction for matching requests; together with released-scale production, these mechanisms define the operational scalability considered here. The representation is evaluated with held-out regression, few-label classification, anomaly-candidate prioritization, and similarity retrieval. Held-out ridge probes yield R2=0.377--$0.596$ across four catalogue quantities. Under a one-percent total labelled budget that includes validation, frozen MLP macro-F1 is 0.802--0.861 for three tasks but 0.484 for the strongly imbalanced spiral task; limited final-block fine-tuning gives 0.810--0.850 for those three tasks and 0.520 for spiral. The historical anomaly workflow identifies 1,681 configuration-dependent candidates, and the displayed examples illustrate image-quality failures without estimating their prevalence. These results show that a standardized image interface and a reusable pretrained embedding can support several downstream analyses at the scale of the released Euclid Q1 sample, while the quantitative performance and interpretation remain task dependent under the declared input and evaluation contracts.
Related
- A Fast and Scalable Transformer Pipeline for Binary Black Hole Detection
- The assembly of bulge-dominated galaxies: two evolutionary channels traced through morphology, kinematics, and environment with a hybrid classification pipeline
- Flow-based neural networks for scalable high resolution imaging of VLBI observations
- Flow-based neural networks for scalable high resolution imaging of VLBI observations
- Pushing HST to the limit. Detection completeness and morphology robustness of faint galaxies in the Extended Groth Strip field
BibTeX
@misc{xie2026making,
title = {{Making Euclid VIS Imaging AI-Ready: A Scalable Pipeline for Morphology, Anomaly Detection, and Similarity Search}},
author = {Jinhui Xie and Yunfei Xu and Zhen Zhang and Lang Chen and Chenzhou Cui},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.32753},
eprint = {2609.32753},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.32753},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Making Euclid VIS Imaging AI-Ready: A Scalable Pipeline for Morphology, Anomaly Detection, and Similarity Search
AU - Jinhui Xie
AU - Yunfei Xu
AU - Zhen Zhang
AU - Lang Chen
AU - Chenzhou Cui
PY - 2026
DA - 2026/09/26
PB - arXiv
DO - 10.48550/arxiv.2609.32753
UR - https://arxiv.org/abs/2609.32753
AB - The Euclid mission is delivering an unprecedented volume of high-resolution galaxy imaging, posing new challenges for standardized and reproducible reuse across morphological analyses. We present a scalable pipeline that converts released VIS cutouts into standardized 224×224 model inputs and uses a pretrained DINOv2 ViT-S/14 feature extractor to construct a 365,513-row, 384-dimensional cutout-and-embedding product from the Galaxy Zoo Euclid (Q1) catalogue. Initial production of the 365,513 released cutouts required approximately 48 hours, corresponding to an estimated end-to-end rate of $2.12$ cutouts s^−1. The service supports batch task management, while persistent reuse of generated products avoids repeating mosaic extraction for matching requests; together with released-scale production, these mechanisms define the operational scalability considered here. The representation is evaluated with held-out regression, few-label classification, anomaly-candidate prioritization, and similarity retrieval. Held-out ridge probes yield R^2=0.377--$0.596$ across four catalogue quantities. Under a one-percent total labelled budget that includes validation, frozen MLP macro-F1 is 0.802--0.861 for three tasks but 0.484 for the strongly imbalanced spiral task; limited final-block fine-tuning gives 0.810--0.850 for those three tasks and 0.520 for spiral. The historical anomaly workflow identifies 1,681 configuration-dependent candidates, and the displayed examples illustrate image-quality failures without estimating their prevalence. These results show that a standardized image interface and a reusable pretrained embedding can support several downstream analyses at the scale of the released Euclid Q1 sample, while the quantitative performance and interpretation remain task dependent under the declared input and evaluation contracts.
ER -