{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/part-detector-discovery-in-deep-convolutional","title":"Part Detector Discovery in Deep Convolutional Neural Networks","arxiv_id":"1411.3159","date":"2014-11-12","proceeding":null,"authors":["Marcel Simon","Erik Rodner","Joachim Denzler"],"abstract":"Current fine-grained classification approaches often rely on a robust\nlocalization of object parts to extract localized feature representations\nsuitable for discrimination. However, part localization is a challenging task\ndue to the large variation of appearance and pose. In this paper, we show how\npre-trained convolutional neural networks can be used for robust and efficient\nobject part discovery and localization without the necessity to actually train\nthe network on the current dataset. Our approach called \"part detector\ndiscovery\" (PDD) is based on analyzing the gradient maps of the network outputs\nand finding activation centers spatially related to annotated semantic parts or\nbounding boxes.\n  This allows us not just to obtain excellent performance on the CUB200-2011\ndataset, but in contrast to previous approaches also to perform detection and\nbird classification jointly without requiring a given bounding box annotation\nduring testing and ground-truth parts during training. The code is available at\nhttp://www.inf-cv.uni-jena.de/part_discovery and\nhttps://github.com/cvjena/PartDetectorDisovery.","url_abs":"http://arxiv.org/abs/1411.3159v2","url_pdf":"http://arxiv.org/pdf/1411.3159v2.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":"part-detector-discovery-in-deep-convolutional","repo_url":"https://github.com/cvjena/PartDetectorDisovery","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"cvjena/PartDetectorDisovery","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"96dd0b01855b7b1a09157ac75f521a01174e15606d6405d599031a4365af7b3b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}