{"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/shorten-spatial-spectral-rnn-with-parallel","title":"Shorten Spatial-spectral RNN with Parallel-GRU for Hyperspectral Image Classification","arxiv_id":"1810.12563","date":"2018-10-30","proceeding":null,"authors":["Haowen Luo"],"abstract":"Convolutional neural networks (CNNs) attained a good performance in\nhyperspectral sensing image (HSI) classification, but CNNs consider spectra as\norderless vectors. Therefore, considering the spectra as sequences, recurrent\nneural networks (RNNs) have been applied in HSI classification, for RNNs is\nskilled at dealing with sequential data. However, for a long-sequence task,\nRNNs is difficult for training and not as effective as we expected. Besides,\nspatial contextual features are not considered in RNNs. In this study, we\npropose a Shorten Spatial-spectral RNN with Parallel-GRU (St-SS-pGRU) for HSI\nclassification. A shorten RNN is more efficient and easier for training than\nband-by-band RNN. By combining converlusion layer, the St-SSpGRU model\nconsiders not only spectral but also spatial feature, which results in a better\nperformance. An architecture named parallel-GRU is also proposed and applied in\nSt-SS-pGRU. With this architecture, the model gets a better performance and is\nmore robust.","url_abs":"http://arxiv.org/abs/1810.12563v1","url_pdf":"http://arxiv.org/pdf/1810.12563v1.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":"shorten-spatial-spectral-rnn-with-parallel","repo_url":"https://github.com/codeRimoe/DL_for_RSIs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"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":[{"leaderboard":"/sota/hyperspectral-image-classification-on-indian","task":"Hyperspectral Image Classification","dataset":"Indian Pines","model":"St-SS-pGRU","rank_in_archive_order":33,"of":34,"metrics":{"Overall Accuracy":"90.35%"},"uses_additional_data":false},{"leaderboard":"/sota/hyperspectral-image-classification-on-pavia","task":"Hyperspectral Image Classification","dataset":"Pavia University","model":"St-SS-pGRU","rank_in_archive_order":29,"of":33,"metrics":{"Overall Accuracy":"98.44%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}