{"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/count-ception-counting-by-fully-convolutional","title":"Count-ception: Counting by Fully Convolutional Redundant Counting","arxiv_id":"1703.08710","date":"2017-03-25","proceeding":null,"authors":["Joseph Paul Cohen","Genevieve Boucher","Craig A. Glastonbury","Henry Z. Lo","Yoshua Bengio"],"abstract":"Counting objects in digital images is a process that should be replaced by\nmachines. This tedious task is time consuming and prone to errors due to\nfatigue of human annotators. The goal is to have a system that takes as input\nan image and returns a count of the objects inside and justification for the\nprediction in the form of object localization. We repose a problem, originally\nposed by Lempitsky and Zisserman, to instead predict a count map which contains\nredundant counts based on the receptive field of a smaller regression network.\nThe regression network predicts a count of the objects that exist inside this\nframe. By processing the image in a fully convolutional way each pixel is going\nto be accounted for some number of times, the number of windows which include\nit, which is the size of each window, (i.e., 32x32 = 1024). To recover the true\ncount we take the average over the redundant predictions. Our contribution is\nredundant counting instead of predicting a density map in order to average over\nerrors. We also propose a novel deep neural network architecture adapted from\nthe Inception family of networks called the Count-ception network. Together our\napproach results in a 20% relative improvement (2.9 to 2.3 MAE) over the state\nof the art method by Xie, Noble, and Zisserman in 2016.","url_abs":"http://arxiv.org/abs/1703.08710v2","url_pdf":"http://arxiv.org/pdf/1703.08710v2.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":"count-ception-counting-by-fully-convolutional","repo_url":"https://github.com/ieee8023/countception","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"count-ception-counting-by-fully-convolutional","repo_url":"https://github.com/roggirg/count-ception_mbm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.08710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.08710"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ieee8023/countception","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/roggirg/count-ception_mbm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"30431ec96b0a7625","entry":"getCellCountCells","repo":"roggirg/count-ception_mbm","repo_kind":"listed","path":"utils/create_datafiles.py","file_url":"https://github.com/roggirg/count-ception_mbm/blob/HEAD/utils/create_datafiles.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30431ec96b0a7625"}},{"code_sha256_prefix":"6cf29f2985b712d0","entry":"getLabelsCells","repo":"roggirg/count-ception_mbm","repo_kind":"listed","path":"utils/create_datafiles.py","file_url":"https://github.com/roggirg/count-ception_mbm/blob/HEAD/utils/create_datafiles.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6cf29f2985b712d0"}},{"code_sha256_prefix":"3bf86e48b409ed20","entry":"getMarkersCells","repo":"roggirg/count-ception_mbm","repo_kind":"listed","path":"utils/create_datafiles.py","file_url":"https://github.com/roggirg/count-ception_mbm/blob/HEAD/utils/create_datafiles.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bf86e48b409ed20"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}