{"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/galaxy-morphology-prediction-using-capsule","title":"Galaxy morphology prediction using capsule networks","arxiv_id":"1809.08377","date":"2018-09-22","proceeding":null,"authors":["Reza Katebi","Yadi Zhou","Ryan Chornock","Razvan Bunescu"],"abstract":"Understanding morphological types of galaxies is a key parameter for studying\ntheir formation and evolution. Neural networks that have been used previously\nfor galaxy morphology classification have some disadvantages, such as not being\ninvariant under rotation. In this work, we studied the performance of Capsule\nNetwork, a recently introduced neural network architecture that is rotationally\ninvariant and spatially aware, on the task of galaxy morphology classification.\nWe designed two evaluation scenarios based on the answers from the question\ntree in the Galaxy Zoo project. In the first scenario, we used Capsule Network\nfor regression and predicted probabilities for all of the questions. In the\nsecond scenario, we chose the answer to the first morphology question that had\nthe highest user agreement as the class of the object and trained a Capsule\nNetwork classifier, where we also reconstructed galaxy images. We achieved\npromising results in both of these scenarios. Automated approaches such as the\none introduced here will greatly decrease the workload of astronomers and will\nplay a critical role in the upcoming large sky surveys.","url_abs":"http://arxiv.org/abs/1809.08377v1","url_pdf":"http://arxiv.org/pdf/1809.08377v1.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":"galaxy-morphology-prediction-using-capsule","repo_url":"https://github.com/RezaKatebi/Galaxy-Morphology-CapsNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"morphology-classification","task_name":"Morphology classification"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.08377","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}