{"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/truncating-wide-networks-using-binary-tree","title":"Truncating Wide Networks using Binary Tree Architectures","arxiv_id":"1704.00509","date":"2017-04-03","proceeding":"ICCV 2017 10","authors":["Yan Zhang","Mete Ozay","Shuo-Hao Li","Takayuki Okatani"],"abstract":"Recent study shows that a wide deep network can obtain accuracy comparable to\na deeper but narrower network. Compared to narrower and deeper networks, wide\nnetworks employ relatively less number of layers and have various important\nbenefits, such that they have less running time on parallel computing devices,\nand they are less affected by gradient vanishing problems. However, the\nparameter size of a wide network can be very large due to use of large width of\neach layer in the network. In order to keep the benefits of wide networks\nmeanwhile improve the parameter size and accuracy trade-off of wide networks,\nwe propose a binary tree architecture to truncate architecture of wide networks\nby reducing the width of the networks. More precisely, in the proposed\narchitecture, the width is continuously reduced from lower layers to higher\nlayers in order to increase the expressive capacity of network with a less\nincrease on parameter size. Also, to ease the gradient vanishing problem,\nfeatures obtained at different layers are concatenated to form the output of\nour architecture. By employing the proposed architecture on a baseline wide\nnetwork, we can construct and train a new network with same depth but\nconsiderably less number of parameters. In our experimental analyses, we\nobserve that the proposed architecture enables us to obtain better parameter\nsize and accuracy trade-off compared to baseline networks using various\nbenchmark image classification datasets. The results show that our model can\ndecrease the classification error of baseline from 20.43% to 19.22% on\nCifar-100 using only 28% of parameters that baseline has. Code is available at\nhttps://github.com/ZhangVision/bitnet.","url_abs":"http://arxiv.org/abs/1704.00509v1","url_pdf":"http://arxiv.org/pdf/1704.00509v1.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":"truncating-wide-networks-using-binary-tree","repo_url":"https://github.com/ZhangVision/bitnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-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":"ZhangVision/bitnet","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":"ca82ef98b69631a62c56c1a397a3b6ee503db4b51ab7d85d3cf0a2ebbe4aaa93","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}