{"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/fast-dynamic-routing-based-on-weighted-kernel","title":"Fast Dynamic Routing Based on Weighted Kernel Density Estimation","arxiv_id":"1805.10807","date":"2018-05-28","proceeding":null,"authors":["Suofei Zhang","Wei Zhao","Xiaofu Wu","Quan Zhou"],"abstract":"Capsules as well as dynamic routing between them are most recently proposed\nstructures for deep neural networks. A capsule groups data into vectors or\nmatrices as poses rather than conventional scalars to represent specific\nproperties of target instance. Besides of pose, a capsule should be attached\nwith a probability (often denoted as activation) for its presence. The dynamic\nrouting helps capsules achieve more generalization capacity with many fewer\nmodel parameters. However, the bottleneck that prevents widespread applications\nof capsule is the expense of computation during routing. To address this\nproblem, we generalize existing routing methods within the framework of\nweighted kernel density estimation, and propose two fast routing methods with\ndifferent optimization strategies. Our methods prompt the time efficiency of\nrouting by nearly 40\\% with negligible performance degradation. By stacking a\nhybrid of convolutional layers and capsule layers, we construct a network\narchitecture to handle inputs at a resolution of $64\\times{64}$ pixels. The\nproposed models achieve a parallel performance with other leading methods in\nmultiple benchmarks.","url_abs":"http://arxiv.org/abs/1805.10807v2","url_pdf":"http://arxiv.org/pdf/1805.10807v2.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":"fast-dynamic-routing-based-on-weighted-kernel","repo_url":"https://github.com/andyweizhao/capsule","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"fast-dynamic-routing-based-on-weighted-kernel","repo_url":"https://github.com/andyweizhao/capsule_text_classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"fast-dynamic-routing-based-on-weighted-kernel","repo_url":"https://github.com/kevindeangeli/capsuleNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-smallnorb","task":"Image Classification","dataset":"smallNORB","model":"FRMS","rank_in_archive_order":5,"of":7,"metrics":{"Classification Error":"2.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.10807","atlas_url":"https://app.syntology.ai/?focus=1805.10807","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":"1805.10807"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1805.10807\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1805.10807"},"call":"get_concepts_for_paper(arxiv_id=\"1805.10807\")"}],"by_repo":[{"repo":"andyweizhao/capsule","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"andyweizhao/capsule_text_classification","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kevindeangeli/capsuleNetwork","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":"36b5a789ecc630e1a5235feb9818cd63e29c7298bf16a42da36a984667030c6e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}