{"url":"/method/cascadepsp","slug":"cascadepsp","name":"CascadePSP","full_name":"CascadePSP","full_name_withheld":false,"description_markdown":"**CascadePSP** is a general segmentation refinement model that refines any given segmentation from low to high resolution. The model takes as input an initial mask that can be an output of any algorithm to provide a rough object location. Then the CascadePSP will output a refined mask. The model is designed in a cascade fashion that generates refined segmentation in a coarse-to-fine manner. Coarse outputs from the early levels predict object structure which will be used as input to the latter levels to refine boundary details.","description_state":"present","introduced_year":null,"introduced_by":{"title":"CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement","paper":"/paper/cascadepsp-toward-class-agnostic-and-very","first_author":"Ho Kei Cheng","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/cascadepsp-toward-class-agnostic-and-very"},"source":{"url":"https://arxiv.org/abs/2005.02551v1","title":"CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Semantic Segmentation Models","url":"/methods/category/semantic-segmentation-models","pwc_aliases":["segmentation-models"]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":"/paper/3rd-place-solution-for-pvuw2023-vss-track-a","title":"3rd Place Solution for PVUW2023 VSS Track: A Large Model for Semantic Segmentation on VSPW","date":"2023-06-04","arxiv_id":"2306.02291","n_code_links":1,"syntology":null},{"paper":"/paper/cascadepsp-toward-class-agnostic-and-very","title":"CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement","date":"2020-05-06","arxiv_id":"2005.02551","n_code_links":2,"syntology":{"ran":2,"of":7,"unverified":5,"pointer_only":0}}],"papers_shown":2,"tasks":[{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/4k","name":"4k","papers":1},{"task":"/task/land-cover-classification","name":"Land Cover Classification","papers":1},{"task":null,"name":"Position","papers":1},{"task":"/task/scene-parsing","name":"Scene Parsing","papers":1},{"task":"/task/video-semantic-segmentation","name":"Video Semantic Segmentation","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2020","papers":1},{"year":"2023","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/cascadepsp"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}