{"url":"/method/coordconv","slug":"coordconv","name":"CoordConv","full_name":"CoordConv","full_name_withheld":false,"description_markdown":"A **CoordConv** layer is a simple extension to the standard convolutional layer. It has the same functional signature as a convolutional layer, but accomplishes the mapping by first concatenating extra channels to the incoming representation. These channels contain hard-coded coordinates, the most basic version of which is one channel for the $i$ coordinate and one for the $j$ coordinate.\r\n\r\nThe CoordConv layer keeps the properties of few parameters and efficient computation from convolutions, but allows the network to learn to keep or to discard translation invariance as is needed for the task being learned. This is useful for coordinate transform based tasks where regular convolutions can fail.","description_state":"present","introduced_year":null,"introduced_by":{"title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","paper":"/paper/an-intriguing-failing-of-convolutional-neural","first_author":"Rosanne Liu","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/an-intriguing-failing-of-convolutional-neural"},"source":{"url":"http://arxiv.org/abs/1807.03247v2","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/uber-research/CoordConv/blob/27fab8b86efac87c262c7c596a0c384b83c9d806/CoordConv.py#L87","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutions","url":"/methods/category/convolutions","pwc_aliases":[]}],"n_papers_tagged":16,"archive_num_papers":16,"papers_newest_first":[{"paper":"/paper/mammographic-breast-positioning-assessment","title":"Mammographic Breast Positioning Assessment via Deep Learning","date":"2024-07-15","arxiv_id":"2407.10796","n_code_links":1,"syntology":null},{"paper":"/paper/semi-supervised-domain-adaptation-for-5","title":"Semi-Supervised Domain Adaptation for Wildfire Detection","date":"2024-04-02","arxiv_id":"2404.01842","n_code_links":1,"syntology":null},{"paper":null,"title":"YOLOrtho -- A Unified Framework for Teeth Enumeration and Dental Disease Detection","date":"2023-08-11","arxiv_id":"2308.05967","n_code_links":0,"syntology":null},{"paper":"/paper/pp-yoloe-an-evolved-version-of-yolo","title":"PP-YOLOE: An evolved version of YOLO","date":"2022-03-30","arxiv_id":"2203.16250","n_code_links":8,"syntology":{"ran":5,"of":27,"unverified":22,"pointer_only":0}},{"paper":null,"title":"In Defense of Kalman Filtering for Polyp Tracking from Colonoscopy Videos","date":"2022-01-27","arxiv_id":"2201.11450","n_code_links":0,"syntology":null},{"paper":"/paper/depth-aware-object-segmentation-and-grasp","title":"Depth-aware Object Segmentation and Grasp Detection for Robotic Picking Tasks","date":"2021-11-22","arxiv_id":"2111.11114","n_code_links":1,"syntology":null},{"paper":"/paper/segmentation-of-drilled-holes-in-texture","title":"Segmentation of Drilled Holes in Texture Wooden Furniture Panels Using Deep Neural Network","date":"2021-05-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/pp-yolov2-a-practical-object-detector","title":"PP-YOLOv2: A Practical Object Detector","date":"2021-04-21","arxiv_id":"2104.10419","n_code_links":1,"syntology":null},{"paper":"/paper/an-efficient-multitask-neural-network-for","title":"An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking","date":"2021-03-13","arxiv_id":"2103.07615","n_code_links":0,"syntology":null},{"paper":"/paper/pp-yolo-an-effective-and-efficient","title":"PP-YOLO: An Effective and Efficient Implementation of Object Detector","date":"2020-07-23","arxiv_id":"2007.12099","n_code_links":5,"syntology":null},{"paper":"/paper/propagationnet-propagate-points-to-curve-to-1","title":"PropagationNet: Propagate Points to Curve to Learn Structure Information","date":"2020-06-25","arxiv_id":"2006.14308","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep feature fusion for self-supervised monocular depth prediction","date":"2020-05-16","arxiv_id":"2005.07922","n_code_links":0,"syntology":null},{"paper":null,"title":"Segmentation-based Method combined with Dynamic Programming for Brain Midline Delineation","date":"2020-02-27","arxiv_id":"2002.11918","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-wing-loss-for-robust-face-alignment","title":"Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression","date":"2019-04-16","arxiv_id":"1904.07399","n_code_links":7,"syntology":{"ran":7,"of":27,"unverified":20,"pointer_only":1}},{"paper":"/paper/181201429","title":"Automatic salt deposits segmentation: A deep learning approach","date":"2018-11-21","arxiv_id":"1812.01429","n_code_links":2,"syntology":null},{"paper":"/paper/an-intriguing-failing-of-convolutional-neural","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","date":"2018-07-09","arxiv_id":"1807.03247","n_code_links":24,"syntology":{"ran":4,"of":5,"unverified":1,"pointer_only":0}}],"papers_shown":16,"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":5},{"task":"/task/object-detection-1","name":"object-detection","papers":4},{"task":"/task/face-alignment","name":"Face Alignment","papers":3},{"task":"/task/object","name":"Object","papers":3},{"task":"/task/segmentation","name":"Segmentation","papers":3},{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/deep-learning","name":"Deep Learning","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/2d-object-detection","name":"2D Object Detection","papers":1},{"task":"/task/2d-semantic-segmentation","name":"2D Semantic Segmentation","papers":1},{"task":"/task/anatomical-landmark-detection","name":"Anatomical Landmark Detection","papers":1},{"task":"/task/atari-games","name":"Atari Games","papers":1},{"task":"/task/breast-tissue-identification","name":"Breast Tissue Identification","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1},{"task":"/task/dense-object-detection","name":"Dense Object Detection","papers":1},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":1},{"task":"/task/depth-prediction","name":"Depth Prediction","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":1}],"tasks_shown":20,"n_tasks":36,"usage_by_year":[{"year":"2018","papers":2},{"year":"2019","papers":1},{"year":"2020","papers":4},{"year":"2021","papers":4},{"year":"2022","papers":2},{"year":"2023","papers":1},{"year":"2024","papers":2}],"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/coordconv"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}