{"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/semantic-binary-segmentation-using","title":"Semantic Binary Segmentation using Convolutional Networks without Decoders","arxiv_id":"1805.00138","date":"2018-05-01","proceeding":null,"authors":["Shubhra Aich","William van der Kamp","Ian Stavness"],"abstract":"In this paper, we propose an efficient architecture for semantic image\nsegmentation using the depth-to-space (D2S) operation. Our D2S model is\ncomprised of a standard CNN encoder followed by a depth-to-space reordering of\nthe final convolutional feature maps. Our approach eliminates the decoder\nportion of traditional encoder-decoder segmentation models and reduces the\namount of computation almost by half. As a participant of the DeepGlobe Road\nExtraction competition, we evaluate our models on the corresponding road\nsegmentation dataset. Our highly efficient D2S models exhibit comparable\nperformance to standard segmentation models with much lower computational cost.","url_abs":"http://arxiv.org/abs/1805.00138v2","url_pdf":"http://arxiv.org/pdf/1805.00138v2.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":"semantic-binary-segmentation-using","repo_url":"https://github.com/littleaich/deepglobe2018","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"road-segementation","task_name":"Road Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}