{"url":"/method/precise-roi-pooling","slug":"precise-roi-pooling","name":"Precise RoI Pooling","full_name":"Precise RoI Pooling","full_name_withheld":false,"description_markdown":"**Precise RoI Pooling**, or **PrRoI Pooling**, is a region of interest feature extractor that avoids any quantization of coordinates and has a continuous gradient on bounding box coordinates. Given the feature map $\\mathcal{F}$ before RoI/PrRoI Pooling (eg from Conv4 in [ResNet](https://paperswithcode.com/method/resnet)-50), let $w_{i,j}$ be the feature at one discrete location $(i,j)$ on the feature map. Using bilinear interpolation, the discrete feature map can be considered continuous at any continuous coordinates $(x,y)$:\r\n\r\n$$\r\nf(x,y) = \\sum_{i,j}IC(x,y,i,j) \\times w_{i,j},\r\n$$\r\n\r\nwhere $IC(x,y,i,j) = max(0,1-|x-i|)\\times max(0,1-|y-j|)$ is the interpolation coefficient. Then denote a bin of a RoI as $bin=\\{(x_1,y_1),(x_2,y_2)\\}$, where $(x_1,y_1)$ and $(x_2,y_2)$ are the continuous coordinates of the top-left and bottom-right points, respectively. We perform pooling (e.g. [average pooling](https://paperswithcode.com/method/average-pooling)) given $bin$ and feature map $\\mathcal{F}$ by computing a two-order integral:","description_state":"present","introduced_year":null,"introduced_by":{"title":"Acquisition of Localization Confidence for Accurate Object Detection","paper":"/paper/acquisition-of-localization-confidence-for","first_author":"Borui Jiang","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/acquisition-of-localization-confidence-for"},"source":{"url":"http://arxiv.org/abs/1807.11590v1","title":"Acquisition of Localization Confidence for Accurate Object Detection","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/vacancy/PreciseRoIPooling/blob/070a7950db6a945e30e8e3296204a1e975f131e8/pytorch/prroi_pool/prroi_pool.py#L19","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"RoI Feature Extractors","url":"/methods/category/roi-feature-extractors","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":null,"title":"3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds","date":"2020-04-10","arxiv_id":"2004.04962","n_code_links":0,"syntology":null},{"paper":"/paper/multi-modal-fusion-for-end-to-end-rgb-t","title":"Multi-Modal Fusion for End-to-End RGB-T Tracking","date":"2019-08-30","arxiv_id":"1908.11714","n_code_links":1,"syntology":null},{"paper":"/paper/hybrid-task-cascade-for-instance-segmentation","title":"Hybrid Task Cascade for Instance Segmentation","date":"2019-01-22","arxiv_id":"1901.07518","n_code_links":5,"syntology":{"ran":0,"of":11,"unverified":11,"pointer_only":0}},{"paper":"/paper/acquisition-of-localization-confidence-for","title":"Acquisition of Localization Confidence for Accurate Object Detection","date":"2018-07-30","arxiv_id":"1807.11590","n_code_links":4,"syntology":{"ran":2,"of":18,"unverified":16,"pointer_only":0}}],"papers_shown":4,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/regression-1","name":"regression","papers":2},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/image-to-image-translation","name":"Image-to-Image Translation","papers":1},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/open-question","name":"Open-Ended Question Answering","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1},{"task":"/task/rgb-t-tracking","name":"Rgb-T Tracking","papers":1},{"task":"/task/segmentation","name":"Segmentation","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1}],"tasks_shown":12,"n_tasks":12,"usage_by_year":[{"year":"2018","papers":1},{"year":"2019","papers":2},{"year":"2020","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/precise-roi-pooling"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}