{"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/stacked-deconvolutional-network-for-semantic","title":"Stacked Deconvolutional Network for Semantic Segmentation","arxiv_id":"1708.04943","date":"2017-08-16","proceeding":null,"authors":["Jun Fu","Jing Liu","Yuhang Wang","Hanqing Lu"],"abstract":"Recent progress in semantic segmentation has been driven by improving the\nspatial resolution under Fully Convolutional Networks (FCNs). To address this\nproblem, we propose a Stacked Deconvolutional Network (SDN) for semantic\nsegmentation. In SDN, multiple shallow deconvolutional networks, which are\ncalled as SDN units, are stacked one by one to integrate contextual information\nand guarantee the fine recovery of localization information. Meanwhile,\ninter-unit and intra-unit connections are designed to assist network training\nand enhance feature fusion since the connections improve the flow of\ninformation and gradient propagation throughout the network. Besides,\nhierarchical supervision is applied during the upsampling process of each SDN\nunit, which guarantees the discrimination of feature representations and\nbenefits the network optimization. We carry out comprehensive experiments and\nachieve the new state-of-the-art results on three datasets, including PASCAL\nVOC 2012, CamVid, GATECH. In particular, our best model without CRF\npost-processing achieves an intersection-over-union score of 86.6% in the test\nset.","url_abs":"http://arxiv.org/abs/1708.04943v1","url_pdf":"http://arxiv.org/pdf/1708.04943v1.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":[],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-pascal-voc-2012","task":"Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"CASIA_IVA_SDN","rank_in_archive_order":4,"of":51,"metrics":{"Mean IoU":"86.6%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.04943","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}