{"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-u-nets-a-no-frills-approach-to","title":"Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation","arxiv_id":"1804.10343","date":"2018-04-27","proceeding":null,"authors":["Sohil Shah","Pallabi Ghosh","Larry S. Davis","Tom Goldstein"],"abstract":"Many imaging tasks require global information about all pixels in an image.\nConventional bottom-up classification networks globalize information by\ndecreasing resolution; features are pooled and downsampled into a single\noutput. But for semantic segmentation and object detection tasks, a network\nmust provide higher-resolution pixel-level outputs. To globalize information\nwhile preserving resolution, many researchers propose the inclusion of\nsophisticated auxiliary blocks, but these come at the cost of a considerable\nincrease in network size and computational cost. This paper proposes stacked\nu-nets (SUNets), which iteratively combine features from different resolution\nscales while maintaining resolution. SUNets leverage the information\nglobalization power of u-nets in a deeper network architectures that is capable\nof handling the complexity of natural images. SUNets perform extremely well on\nsemantic segmentation tasks using a small number of parameters.","url_abs":"http://arxiv.org/abs/1804.10343v1","url_pdf":"http://arxiv.org/pdf/1804.10343v1.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":"stacked-u-nets-a-no-frills-approach-to","repo_url":"https://github.com/shahsohil/sunets","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic 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}