{"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/residual-pyramid-learning-for-single-shot","title":"Residual Pyramid Learning for Single-Shot Semantic Segmentation","arxiv_id":"1903.09746","date":"2019-03-23","proceeding":null,"authors":["Xiaoyu Chen","Xiaotian Lou","Lianfa Bai","Jing Han"],"abstract":"Pixel-level semantic segmentation is a challenging task with a huge amount of\ncomputation, especially if the size of input is large. In the segmentation\nmodel, apart from the feature extraction, the extra decoder structure is often\nemployed to recover spatial information. In this paper, we put forward a method\nfor single-shot segmentation in a feature residual pyramid network (RPNet),\nwhich learns the main and residuals of segmentation by decomposing the label at\ndifferent levels of residual blocks. Specifically speaking, we use the residual\nfeatures to learn the edges and details, and the identity features to learn the\nmain part of targets. At testing time, the predicted residuals are used to\nenhance the details of the top-level prediction. Residual learning blocks split\nthe network into several shallow sub-networks which facilitates the training of\nthe RPNet. We then evaluate the proposed method and compare it with recent\nstate-of-the-art methods on CamVid and Cityscapes. The proposed single-shot\nsegmentation based on RPNet achieves impressive results with high efficiency on\npixel-level segmentation.","url_abs":"http://arxiv.org/abs/1903.09746v1","url_pdf":"http://arxiv.org/pdf/1903.09746v1.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":"residual-pyramid-learning-for-single-shot","repo_url":"https://github.com/superlxt/RPNet-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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}