{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-galaxy-foundation-models-with-hybrid","title":"Towards Galaxy Foundation Models with Hybrid Contrastive Learning","arxiv_id":"2206.11927","date":"2022-06-23","proceeding":null,"authors":["Mike Walmsley","Inigo Val Slijepcevic","Micah Bowles","Anna M. M. Scaife"],"abstract":"New astronomical tasks are often related to earlier tasks for which labels have already been collected. We adapt the contrastive framework BYOL to leverage those labels as a pretraining task while also enforcing augmentation invariance. For large-scale pretraining, we introduce GZ-Evo v0.1, a set of 96.5M volunteer responses for 552k galaxy images plus a further 1.34M comparable unlabelled galaxies. Most of the 206 GZ-Evo answers are unknown for any given galaxy, and so our pretraining task uses a Dirichlet loss that naturally handles unknown answers. GZ-Evo pretraining, with or without hybrid learning, improves on direct training even with plentiful downstream labels (+4% accuracy with 44k labels). Our hybrid pretraining/contrastive method further improves downstream accuracy vs. pretraining or contrastive learning, especially in the low-label transfer regime (+6% accuracy with 750 labels).","url_abs":"https://arxiv.org/abs/2206.11927v1","url_pdf":"https://arxiv.org/pdf/2206.11927v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-galaxy-foundation-models-with-hybrid","repo_url":"https://github.com/mwalmsley/pytorch-galaxy-datasets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[{"method_slug":"byol","method_name":"BYOL"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.11927","atlas_url":"https://app.syntology.ai/?focus=2206.11927","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}