{"url":"/method/position-sensitive-roi-pooling","slug":"position-sensitive-roi-pooling","name":"Position-Sensitive RoI Pooling","full_name":"Position-Sensitive RoI Pooling","full_name_withheld":false,"description_markdown":"**Position-Sensitive RoI Pooling layer** aggregates the outputs of the last convolutional layer and generates scores for each RoI. Unlike [RoI Pooling](https://paperswithcode.com/method/roi-pooling), PS RoI Pooling conducts selective pooling, and each of the $k$ × $k$ bin aggregates responses from only one score map out of the bank of $k$ × $k$ score maps. With end-to-end training, this RoI layer shepherds the last convolutional layer to learn specialized position-sensitive score maps.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1605.06409v2","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/pytorch/vision/blob/971c3e45b96bc5aa5868c45cd40e4f3c3d90d126/torchvision/ops/ps_roi_pool.py#L10","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":32,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/patchnet-short-range-template-matching-for","title":"PatchNet -- Short-range Template Matching for Efficient Video Processing","date":"2021-03-10","arxiv_id":"2103.07371","n_code_links":1,"syntology":null},{"paper":null,"title":"ABOShips -- An Inshore and Offshore Maritime Vessel Detection Dataset with Precise Annotations","date":"2021-02-11","arxiv_id":"2102.05869","n_code_links":0,"syntology":null},{"paper":"/paper/tensorflow-with-user-friendly-graphical","title":"TensorFlow with user friendly Graphical Framework for object detection API","date":"2020-06-11","arxiv_id":"2006.06385","n_code_links":1,"syntology":null},{"paper":null,"title":"DFR-TSD: A Deep Learning Based Framework for Robust Traffic Sign Detection Under Challenging Weather Conditions","date":"2020-06-03","arxiv_id":"2006.02578","n_code_links":0,"syntology":null},{"paper":null,"title":"KL-Divergence-Based Region Proposal Network for Object Detection","date":"2020-05-22","arxiv_id":"2005.11220","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-safety-of-vulnerable-road-users-by","title":"On the safety of vulnerable road users by cyclist orientation detection using Deep Learning","date":"2020-04-25","arxiv_id":"2004.11909","n_code_links":0,"syntology":null},{"paper":null,"title":"To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis?","date":"2019-09-22","arxiv_id":"1909.09945","n_code_links":0,"syntology":null},{"paper":null,"title":"Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes","date":"2019-08-14","arxiv_id":"1908.05217","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations","date":"2019-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Automatic Traffic Sign Detection and Recognition Using SegU-Net and a Modified Tversky Loss Function With L1-Constraint","date":"2019-04-26","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Large-scale mammography CAD with Deformable Conv-Nets","date":"2019-02-19","arxiv_id":"1902.07323","n_code_links":0,"syntology":null},{"paper":null,"title":"A Comparison of Embedded Deep Learning Methods for Person Detection","date":"2018-12-09","arxiv_id":"1812.03451","n_code_links":0,"syntology":null},{"paper":null,"title":"Fast Object Detection in Compressed Video","date":"2018-11-27","arxiv_id":"1811.11057","n_code_links":0,"syntology":null},{"paper":null,"title":"Satellite Imagery Multiscale Rapid Detection with Windowed Networks","date":"2018-09-25","arxiv_id":"1809.09978","n_code_links":0,"syntology":null},{"paper":null,"title":"Global Weighted Average Pooling Bridges Pixel-level Localization and Image-level Classification","date":"2018-09-21","arxiv_id":"1809.08264","n_code_links":0,"syntology":null},{"paper":null,"title":"DetNet: Design Backbone for Object Detection","date":"2018-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Overhead Detection: Beyond 8-bits and RGB","date":"2018-08-07","arxiv_id":"1808.02443","n_code_links":0,"syntology":null},{"paper":"/paper/the-eurocity-persons-dataset-a-novel","title":"The EuroCity Persons Dataset: A Novel Benchmark for Object Detection","date":"2018-05-18","arxiv_id":"1805.07193","n_code_links":0,"syntology":null},{"paper":null,"title":"Quantization Mimic: Towards Very Tiny CNN for Object Detection","date":"2018-05-06","arxiv_id":"1805.02152","n_code_links":0,"syntology":null},{"paper":"/paper/sliding-line-point-regression-for-shape","title":"Sliding Line Point Regression for Shape Robust Scene Text Detection","date":"2018-01-30","arxiv_id":"1801.09969","n_code_links":1,"syntology":null},{"paper":"/paper/r-fcn-3000-at-30fps-decoupling-detection-and","title":"R-FCN-3000 at 30fps: Decoupling Detection and Classification","date":"2017-12-05","arxiv_id":"1712.01802","n_code_links":2,"syntology":null},{"paper":"/paper/cascade-r-cnn-delving-into-high-quality","title":"Cascade R-CNN: Delving into High Quality Object Detection","date":"2017-12-03","arxiv_id":"1712.00726","n_code_links":8,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":2}},{"paper":"/paper/an-analysis-of-scale-invariance-in-object-1","title":"An Analysis of Scale Invariance in Object Detection - SNIP","date":"2017-11-22","arxiv_id":"1711.08189","n_code_links":0,"syntology":null},{"paper":"/paper/light-head-r-cnn-in-defense-of-two-stage","title":"Light-Head R-CNN: In Defense of Two-Stage Object Detector","date":"2017-11-20","arxiv_id":"1711.07264","n_code_links":5,"syntology":null},{"paper":"/paper/towards-interpretable-r-cnn-by-unfolding","title":"Towards Interpretable R-CNN by Unfolding Latent Structures","date":"2017-11-14","arxiv_id":"1711.05226","n_code_links":1,"syntology":null},{"paper":null,"title":"On Pre-Trained Image Features and Synthetic Images for Deep Learning","date":"2017-10-29","arxiv_id":"1710.10710","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-faces-using-region-based-fully","title":"Detecting Faces Using Region-based Fully Convolutional Networks","date":"2017-09-14","arxiv_id":"1709.05256","n_code_links":1,"syntology":null},{"paper":"/paper/couplenet-coupling-global-structure-with","title":"CoupleNet: Coupling Global Structure with Local Parts for Object Detection","date":"2017-08-09","arxiv_id":"1708.02863","n_code_links":3,"syntology":null},{"paper":"/paper/soft-nms-improving-object-detection-with-one","title":"Soft-NMS -- Improving Object Detection With One Line of Code","date":"2017-04-14","arxiv_id":"1704.04503","n_code_links":8,"syntology":{"ran":4,"of":4,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Object Detection via Aspect Ratio and Context Aware Region-based Convolutional Networks","date":"2016-12-02","arxiv_id":"1612.00534","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":24},{"task":"/task/object-detection-1","name":"object-detection","papers":22},{"task":"/task/object","name":"Object","papers":18},{"task":"/task/region-proposal","name":"Region Proposal","papers":4},{"task":"/task/classification","name":"General Classification","papers":3},{"task":null,"name":"Position","papers":3},{"task":"/task/image-classification","name":"image-classification","papers":3},{"task":"/task/classification-1","name":"Classification","papers":2},{"task":"/task/deep-learning","name":"Deep Learning","papers":2},{"task":"/task/image-classification","name":"Image Classification","papers":2},{"task":"/task/object-recognition","name":"Object Recognition","papers":2},{"task":"/task/real-time-object-detection","name":"Real-Time Object Detection","papers":2},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":2},{"task":"/task/traffic-sign-detection","name":"Traffic Sign Detection","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/2d-cyclist-detection","name":"2D Cyclist Detection","papers":1},{"task":"/task/2d-object-detection","name":"2D Object Detection","papers":1},{"task":"/task/arc","name":"ARC","papers":1},{"task":"/task/autonomous-vehicles","name":"Autonomous Vehicles","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1}],"tasks_shown":20,"n_tasks":52,"usage_by_year":[{"year":"2016","papers":3},{"year":"2017","papers":9},{"year":"2018","papers":9},{"year":"2019","papers":5},{"year":"2020","papers":4},{"year":"2021","papers":2}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/position-sensitive-roi-pooling"},"syntology_read_at":"2026-09-25T09:33:49+00:00"}