A shared-weights two-branch Swin Transformer that processes ZTF and ATLAS light curves jointly reaches 69.9% macro F1, outperforming single-survey models and simple fusion strategies on 21 classes.
Preliminary Report on Mantis Shrimp: a Multi-Survey Computer Vision Photometric Redshift Model
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
The availability of large, public, multi-modal astronomical datasets presents an opportunity to execute novel research that straddles the line between science of AI and science of astronomy. Photometric redshift estimation is a well-established subfield of astronomy. Prior works show that computer vision models typically outperform catalog-based models, but these models face additional complexities when incorporating images from more than one instrument or sensor. In this report, we detail our progress creating Mantis Shrimp, a multi-survey computer vision model for photometric redshift estimation that fuses ultra-violet (GALEX), optical (PanSTARRS), and infrared (UnWISE) imagery. We use deep learning interpretability diagnostics to measure how the model leverages information from the different inputs. We reason about the behavior of the CNNs from the interpretability metrics, specifically framing the result in terms of physically-grounded knowledge of galaxy properties.
fields
astro-ph.IM 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Image-Based Multi-Survey Classification of Light Curves with a Pre-Trained Vision Transformer
A shared-weights two-branch Swin Transformer that processes ZTF and ATLAS light curves jointly reaches 69.9% macro F1, outperforming single-survey models and simple fusion strategies on 21 classes.