Metraipolis › archive › dc_5ceead3122db
Contrastive Astromer: Two-Stage Contrastive Representation Learning for Astronomical Light Curve Classification — arXiv:2611.00150
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00150
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:43:37.087Z
- SHA-256 of the archived text
8ecd8c2f2d93a939a695d6f45ff7a8e0a547f56bdf04be527e47a17268a770bc- Stable URL of this page
https://metraipolis.com/documento/dc_5ceead3122db
How to cite
Contrastive Astromer: Two-Stage Contrastive Representation Learning for Astronomical Light Curve Classification — arXiv:2611.00150 — arXiv (en), https://arxiv.org/abs/2611.00150 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ceead3122db (Metraipolis archive dc_5ceead3122db, sha256 8ecd8c2f2d93a939a695d6f45ff7a8e0a547f56bdf04be527e47a17268a770bc)
BibTeX
@misc{dc5ceead3122db,
title = {Contrastive Astromer: Two-Stage Contrastive Representation Learning for Astronomical Light Curve Classification — arXiv:2611.00150},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00150},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ceead3122db; sha256 8ecd8c2f2d93a939a695d6f45ff7a8e0a547f56bdf04be527e47a17268a770bc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00150. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large astronomical surveys collect abundant light curves, but reliable class labels remain scarce. ASTROMER 2 learns from unlabeled light curves by reconstructing masked observations, yet this objective does not explicitly encourage class separation in a compact representation of each light curve. We introduce Contrastive Astromer, a two-stage approach that makes these representations more useful for classification without changing the ASTROMER 2 encoder architecture. First, unsupervised contrastive learning on single-band MACHO light curves brings together representations of augmented views of the same object. Supervised contrastive learning, supported by an auxiliary classification loss, then uses a separate labeled Alcock sample to strengthen class discrimination. We evaluate the resulting representations by freezing the encoder and training a separate classifier. On a held-out set of 600 objects, this classifier achieves a macro-F1 of 0.7943 with 500 labeled examples per class, exceeding our reproduction of the ASTROMER 2 finetune-and-classify pipeline by 5.10 percentage points. With downstream classifier training budgets of 20 and 100 examples per class, macro-F1 reaches 0.7078 and 0.7704, respectively, also surpassing this baseline. Embedding-space analyses further show that supervised adaptation improves local class consistency and global class separation. These results show that contrastive adaptation makes pretrained light-curve representations more effective for classification and more informative about the structure of variability classes. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Instrumentation and Methods for Astrophysics (astro-ph.IM) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.00150 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T11:06:37.666Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).