{"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/adaptive-pooling-operators-for-weakly-labeled","title":"Adaptive pooling operators for weakly labeled sound event detection","arxiv_id":"1804.10070","date":"2018-04-26","proceeding":null,"authors":["Brian McFee","Justin Salamon","Juan Pablo Bello"],"abstract":"Sound event detection (SED) methods are tasked with labeling segments of\naudio recordings by the presence of active sound sources. SED is typically\nposed as a supervised machine learning problem, requiring strong annotations\nfor the presence or absence of each sound source at every time instant within\nthe recording. However, strong annotations of this type are both labor- and\ncost-intensive for human annotators to produce, which limits the practical\nscalability of SED methods.\n  In this work, we treat SED as a multiple instance learning (MIL) problem,\nwhere training labels are static over a short excerpt, indicating the presence\nor absence of sound sources but not their temporal locality. The models,\nhowever, must still produce temporally dynamic predictions, which must be\naggregated (pooled) when comparing against static labels during training. To\nfacilitate this aggregation, we develop a family of adaptive pooling\noperators---referred to as auto-pool---which smoothly interpolate between\ncommon pooling operators, such as min-, max-, or average-pooling, and\nautomatically adapt to the characteristics of the sound sources in question. We\nevaluate the proposed pooling operators on three datasets, and demonstrate that\nin each case, the proposed methods outperform non-adaptive pooling operators\nfor static prediction, and nearly match the performance of models trained with\nstrong, dynamic annotations. The proposed method is evaluated in conjunction\nwith convolutional neural networks, but can be readily applied to any\ndifferentiable model for time-series label prediction.","url_abs":"http://arxiv.org/abs/1804.10070v2","url_pdf":"http://arxiv.org/pdf/1804.10070v2.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":"adaptive-pooling-operators-for-weakly-labeled","repo_url":"https://github.com/marl/autopool","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adaptive-pooling-operators-for-weakly-labeled","repo_url":"https://github.com/benbogart/bird_vocalization_classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"sound-event-detection","task_name":"Sound Event Detection"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.10070","atlas_url":"https://app.syntology.ai/?focus=1804.10070","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1804.10070"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1804.10070\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1804.10070"},"call":"get_concepts_for_paper(arxiv_id=\"1804.10070\")"}],"by_repo":[{"repo":"marl/autopool","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"benbogart/bird_vocalization_classification","kind":"listed","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":"01bde581bb2b887962b249c74e5ff27719585fce7cd90fa9394154dd2feaa00e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}