{"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/salient-object-detection-on-hyperspectral","title":"Salient object detection on hyperspectral images using features learned from unsupervised segmentation task","arxiv_id":"1902.10993","date":"2019-02-28","proceeding":null,"authors":["Nevrez Imamoglu","Guanqun Ding","Yuming Fang","Asako Kanezaki","Toru Kouyama","Ryosuke Nakamura"],"abstract":"Various saliency detection algorithms from color images have been proposed to\nmimic eye fixation or attentive object detection response of human observers\nfor the same scenes. However, developments on hyperspectral imaging systems\nenable us to obtain redundant spectral information of the observed scenes from\nthe reflected light source from objects. A few studies using low-level features\non hyperspectral images demonstrated that salient object detection can be\nachieved. In this work, we proposed a salient object detection model on\nhyperspectral images by applying manifold ranking (MR) on self-supervised\nConvolutional Neural Network (CNN) features (high-level features) from\nunsupervised image segmentation task. Self-supervision of CNN continues until\nclustering loss or saliency maps converges to a defined error between each\niteration. Finally, saliency estimations is done as the saliency map at last\niteration when the self-supervision procedure terminates with convergence.\nExperimental evaluations demonstrated that proposed saliency detection\nalgorithm on hyperspectral images is outperforming state-of-the-arts\nhyperspectral saliency models including the original MR based saliency model.","url_abs":"http://arxiv.org/abs/1902.10993v1","url_pdf":"http://arxiv.org/pdf/1902.10993v1.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":"salient-object-detection-on-hyperspectral","repo_url":"https://github.com/gqding/SUDF","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"salient-object-detection","task_name":"RGB Salient Object Detection"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-image-segmentation","task_name":"Unsupervised Image Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}