{"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/deep-spectral-convolution-network-for","title":"Deep Spectral Convolution Network for HyperSpectral Unmixing","arxiv_id":"1806.08562","date":"2018-06-22","proceeding":null,"authors":["Savas Ozkan","Gozde Bozdagi Akar"],"abstract":"In this paper, we propose a novel hyperspectral unmixing technique based on\ndeep spectral convolution networks (DSCN). Particularly, three important\ncontributions are presented throughout this paper. First, fully-connected\nlinear operation is replaced with spectral convolutions to extract local\nspectral characteristics from hyperspectral signatures with a deeper network\narchitecture. Second, instead of batch normalization, we propose a spectral\nnormalization layer which improves the selectivity of filters by normalizing\ntheir spectral responses. Third, we introduce two fusion configurations that\nproduce ideal abundance maps by using the abstract representations computed\nfrom previous layers. In experiments, we use two real datasets to evaluate the\nperformance of our method with other baseline techniques. The experimental\nresults validate that the proposed method outperforms baselines based on Root\nMean Square Error (RMSE).","url_abs":"http://arxiv.org/abs/1806.08562v1","url_pdf":"http://arxiv.org/pdf/1806.08562v1.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":"deep-spectral-convolution-network-for","repo_url":"https://github.com/savasozkan/dscn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"hyperspectral-unmixing","task_name":"Hyperspectral Unmixing"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}