{"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/ultra-high-resolution-segmentation-with-ultra-1","title":"Ultra-High Resolution Segmentation with Ultra-Rich Context: A Novel Benchmark","arxiv_id":"2305.10899","date":"2023-05-18","proceeding":"CVPR 2023 1","authors":["Deyi Ji","Feng Zhao","Hongtao Lu","Mingyuan Tao","Jieping Ye"],"abstract":"With the increasing interest and rapid development of methods for Ultra-High Resolution (UHR) segmentation, a large-scale benchmark covering a wide range of scenes with full fine-grained dense annotations is urgently needed to facilitate the field. To this end, the URUR dataset is introduced, in the meaning of Ultra-High Resolution dataset with Ultra-Rich Context. As the name suggests, URUR contains amounts of images with high enough resolution (3,008 images of size 5,120x5,120), a wide range of complex scenes (from 63 cities), rich-enough context (1 million instances with 8 categories) and fine-grained annotations (about 80 billion manually annotated pixels), which is far superior to all the existing UHR datasets including DeepGlobe, Inria Aerial, UDD, etc.. Moreover, we also propose WSDNet, a more efficient and effective framework for UHR segmentation especially with ultra-rich context. Specifically, multi-level Discrete Wavelet Transform (DWT) is naturally integrated to release computation burden while preserve more spatial details, along with a Wavelet Smooth Loss (WSL) to reconstruct original structured context and texture with a smooth constrain. Experiments on several UHR datasets demonstrate its state-of-the-art performance. The dataset is available at https://github.com/jankyee/URUR.","url_abs":"https://arxiv.org/abs/2305.10899v1","url_pdf":"https://arxiv.org/pdf/2305.10899v1.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":"ultra-high-resolution-segmentation-with-ultra-1","repo_url":"https://github.com/jankyee/urur","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"land-cover-classification","task_name":"Land Cover Classification"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-inria-aerial-image","task":"Semantic Segmentation","dataset":"INRIA Aerial Image Labeling","model":"WSDNet","rank_in_archive_order":8,"of":8,"metrics":{"mIOU":"0.752"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.10899","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}