{"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/neural-rejuvenation-improving-deep-network","title":"Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization","arxiv_id":"1812.00481","date":"2018-12-02","proceeding":"CVPR 2019 6","authors":["Siyuan Qiao","Zhe Lin","Jianming Zhang","Alan Yuille"],"abstract":"In this paper, we study the problem of improving computational resource\nutilization of neural networks. Deep neural networks are usually\nover-parameterized for their tasks in order to achieve good performances, thus\nare likely to have underutilized computational resources. This observation\nmotivates a lot of research topics, e.g. network pruning, architecture search,\netc. As models with higher computational costs (e.g. more parameters or more\ncomputations) usually have better performances, we study the problem of\nimproving the resource utilization of neural networks so that their potentials\ncan be further realized. To this end, we propose a novel optimization method\nnamed Neural Rejuvenation. As its name suggests, our method detects dead\nneurons and computes resource utilization in real time, rejuvenates dead\nneurons by resource reallocation and reinitialization, and trains them with new\ntraining schemes. By simply replacing standard optimizers with Neural\nRejuvenation, we are able to improve the performances of neural networks by a\nvery large margin while using similar training efforts and maintaining their\noriginal resource usages.","url_abs":"http://arxiv.org/abs/1812.00481v1","url_pdf":"http://arxiv.org/pdf/1812.00481v1.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":"neural-rejuvenation-improving-deep-network","repo_url":"https://github.com/joe-siyuan-qiao/NeuralRejuvenation-CVPR19","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1812.00481","atlas_url":"https://app.syntology.ai/?focus=1812.00481","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":"1812.00481"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1812.00481\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1812.00481"},"call":"get_concepts_for_paper(arxiv_id=\"1812.00481\")"}],"by_repo":[{"repo":"joe-siyuan-qiao/NeuralRejuvenation-CVPR19","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":"b205b1a9cba66f254cfe339fb6bb18a53a8797e8fd2747437579003ffac15e14","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}