{"url":"/method/polarmask","slug":"polarmask","name":"PolarMask","full_name":"PolarMask","full_name_withheld":false,"description_markdown":"**PolarMask** is an anchor-box free and single-shot instance segmentation method. Specifically, PolarMask takes an image as input and predicts the distance from a sampled positive location (ie a candidate object's center) with respect to the object's contour at each angle, and then assembles the predicted points to produce the final mask. There are several benefits to the system: (1) The polar representation unifies instance segmentation (masks) and object detection (bounding boxes) into a single framework (2) Two modules are designed (i.e. soft polar centerness and polar IoU loss) to sample high-quality center examples and optimize polar contour regression, making the performance of PolarMask does not depend on the bounding box prediction results and more efficient in training. (3) PolarMask is fully convolutional and can be embedded into most off-the-shelf detection methods.","description_state":"present","introduced_year":null,"introduced_by":{"title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","paper":"/paper/polarmask-enhanced-polar-representation-for","first_author":"Enze Xie","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/polarmask-enhanced-polar-representation-for"},"source":{"url":"https://arxiv.org/abs/2105.02184v1","title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","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":"Instance Segmentation Modules","url":"/methods/category/instance-segmentation-modules","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":3,"papers_newest_first":[{"paper":null,"title":"MP-PolarMask: A Faster and Finer Instance Segmentation for Concave Images","date":"2024-06-03","arxiv_id":"2406.01356","n_code_links":0,"syntology":null},{"paper":"/paper/applying-eigencontours-to-polarmask-based","title":"Applying Eigencontours to PolarMask-Based Instance Segmentation","date":"2022-08-24","arxiv_id":"2208.11258","n_code_links":1,"syntology":null},{"paper":"/paper/polarmask-enhanced-polar-representation-for","title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","date":"2021-05-05","arxiv_id":"2105.02184","n_code_links":1,"syntology":null}],"papers_shown":3,"tasks":[{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":3},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":3},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/cell-segmentation","name":"Cell Segmentation","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/text-detection","name":"Text Detection","papers":1},{"task":"/task/object-detection-1","name":"object-detection","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2024","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/polarmask"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}