{"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/learning-multi-scale-features-for-foreground","title":"Learning Multi-scale Features for Foreground Segmentation","arxiv_id":"1808.01477","date":"2018-08-04","proceeding":null,"authors":["Long Ang Lim","Hacer Yalim Keles"],"abstract":"Foreground segmentation algorithms aim segmenting moving objects from the\nbackground in a robust way under various challenging scenarios. Encoder-decoder\ntype deep neural networks that are used in this domain recently perform\nimpressive segmentation results. In this work, we propose a novel robust\nencoder-decoder structure neural network that can be trained end-to-end using\nonly a few training examples. The proposed method extends the Feature Pooling\nModule (FPM) of FgSegNet by introducing features fusions inside this module,\nwhich is capable of extracting multi-scale features within images; resulting in\na robust feature pooling against camera motion, which can alleviate the need of\nmulti-scale inputs to the network. Our method outperforms all existing\nstate-of-the-art methods in CDnet2014 dataset by an average overall F-Measure\nof 0.9847. We also evaluate the effectiveness of our method on SBI2015 and UCSD\nBackground Subtraction datasets. The source code of the proposed method is made\navailable at https://github.com/lim-anggun/FgSegNet_v2 .","url_abs":"http://arxiv.org/abs/1808.01477v1","url_pdf":"http://arxiv.org/pdf/1808.01477v1.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":"learning-multi-scale-features-for-foreground","repo_url":"https://github.com/lim-anggun/FgSegNet_v2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"foreground-segmentation","task_name":"Foreground Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.01477","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}