Fusing embedding representations from multiple photometric bands improves transformer-based variable star classification by roughly 10% in F1, with only minor sensitivity to how asynchronously the bands are sampled.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.IM 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multivariate Time-series Transformer Embeddings for Light Curves
Fusing embedding representations from multiple photometric bands improves transformer-based variable star classification by roughly 10% in F1, with only minor sensitivity to how asynchronously the bands are sampled.