{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/precise-detection-in-densely-packed-scenes","title":"Precise Detection in Densely Packed Scenes","arxiv_id":"1904.00853","date":"2019-04-01","proceeding":"CVPR 2019 6","authors":["Eran Goldman","Roei Herzig","Aviv Eisenschtat","Oria Ratzon","Itsik Levi","Jacob Goldberger","Tal Hassner"],"abstract":"Man-made scenes can be densely packed, containing numerous objects, often\nidentical, positioned in close proximity. We show that precise object detection\nin such scenes remains a challenging frontier even for state-of-the-art object\ndetectors. We propose a novel, deep-learning based method for precise object\ndetection, designed for such challenging settings. Our contributions include:\n(1) A layer for estimating the Jaccard index as a detection quality score; (2)\na novel EM merging unit, which uses our quality scores to resolve detection\noverlap ambiguities; finally, (3) an extensive, annotated data set, SKU-110K,\nrepresenting packed retail environments, released for training and testing\nunder such extreme settings. Detection tests on SKU-110K and counting tests on\nthe CARPK and PUCPR+ show our method to outperform existing state-of-the-art\nwith substantial margins. The code and data will be made available on\n\\url{www.github.com/eg4000/SKU110K_CVPR19}.","url_abs":"http://arxiv.org/abs/1904.00853v3","url_pdf":"http://arxiv.org/pdf/1904.00853v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"precise-detection-in-densely-packed-scenes","repo_url":"https://github.com/eg4000/SKU110K_CVPR19","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"precise-detection-in-densely-packed-scenes","repo_url":"https://github.com/skrish13/SKU110K-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"precise-detection-in-densely-packed-scenes","repo_url":"https://github.com/skrish13/SKU110K-evaluation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"precise-detection-in-densely-packed-scenes","repo_url":"https://github.com/tyomj/product_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"precise-detection-in-densely-packed-scenes","repo_url":"https://github.com/Media-Smart/SKU110K-DenseDet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"dense-object-detection","task_name":"Dense Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[{"slug":"sku110k","name":"SKU110K","full_name":"SKU110K"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/dense-object-detection-on-sku-110k","task":"Dense Object Detection","dataset":"SKU-110K","model":"Soft-IoU + EM-Merger unit","rank_in_archive_order":4,"of":5,"metrics":{"AP":"49.2"},"uses_additional_data":false},{"leaderboard":"/sota/object-counting-on-carpk","task":"Object Counting","dataset":"CARPK","model":"Soft-IoU + EM-Merger unit","rank_in_archive_order":7,"of":15,"metrics":{"MAE":"6.77","RMSE":"8.52"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.00853","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}