{"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/hsi-cnn-a-novel-convolution-neural-network","title":"HSI-CNN: A Novel Convolution Neural Network for Hyperspectral Image","arxiv_id":"1802.10478","date":"2018-02-28","proceeding":null,"authors":["Yanan Luo","Jie Zou","Chengfei Yao","Tao Li","Gang Bai"],"abstract":"With the development of deep learning, the performance of hyperspectral image\n(HSI) classification has been greatly improved in recent years. The shortage of\ntraining samples has become a bottleneck for further improvement of\nperformance. In this paper, we propose a novel convolutional neural network\nframework for the characteristics of hyperspectral image data, called HSI-CNN.\nFirstly, the spectral-spatial feature is extracted from a target pixel and its\nneighbors. Then, a number of one-dimensional feature maps, obtained by\nconvolution operation on spectral-spatial features, are stacked into a\ntwo-dimensional matrix. Finally, the two-dimensional matrix considered as an\nimage is fed into standard CNN. This is why we call it HSI-CNN. In addition, we\nalso implements two depth network classification models, called HSI-CNN+XGBoost\nand HSI-CapsNet, in order to compare the performance of our framework.\nExperiments show that the performance of hyperspectral image classification is\nimproved efficiently with HSI-CNN framework. We evaluate the model's\nperformance using four popular HSI datasets, which are the Kennedy Space Center\n(KSC), Indian Pines (IP), Pavia University scene (PU) and Salinas scene (SA).\nAs far as we concerned, HSI-CNN has got the state-of-art accuracy among all\nmethods we have known on these datasets of 99.28%, 99.09%, 99.42%, 98.95%\nseparately.","url_abs":"http://arxiv.org/abs/1802.10478v1","url_pdf":"http://arxiv.org/pdf/1802.10478v1.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":"hsi-cnn-a-novel-convolution-neural-network","repo_url":"https://github.com/eecn/Hyperspectral-Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"hsi-cnn-a-novel-convolution-neural-network","repo_url":"https://github.com/nshaud/DeepHyperX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"hyperspectral-image-classification","task_name":"Hyperspectral Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"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}