{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/dsnas-direct-neural-architecture-search","title":"DSNAS: Direct Neural Architecture Search without Parameter Retraining","arxiv_id":"2002.09128","date":"2020-02-21","proceeding":"CVPR 2020 6","authors":["Shoukang Hu","Sirui Xie","Hehui Zheng","Chunxiao Liu","Jianping Shi","Xunying Liu","Dahua Lin"],"abstract":"If NAS methods are solutions, what is the problem? Most existing NAS methods require two-stage parameter optimization. However, performance of the same architecture in the two stages correlates poorly. In this work, we propose a new problem definition for NAS, task-specific end-to-end, based on this observation. We argue that given a computer vision task for which a NAS method is expected, this definition can reduce the vaguely-defined NAS evaluation to i) accuracy of this task and ii) the total computation consumed to finally obtain a model with satisfying accuracy. Seeing that most existing methods do not solve this problem directly, we propose DSNAS, an efficient differentiable NAS framework that simultaneously optimizes architecture and parameters with a low-biased Monte Carlo estimate. Child networks derived from DSNAS can be deployed directly without parameter retraining. Comparing with two-stage methods, DSNAS successfully discovers networks with comparable accuracy (74.4%) on ImageNet in 420 GPU hours, reducing the total time by more than 34%. Our implementation is available at https://github.com/SNAS-Series/SNAS-Series.","url_abs":"https://arxiv.org/abs/2002.09128v2","url_pdf":"https://arxiv.org/pdf/2002.09128v2.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":"dsnas-direct-neural-architecture-search","repo_url":"https://github.com/SNAS-Series/SNAS-Series","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[{"method_slug":"differentiable-nas","method_name":"Differentiable NAS"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201-2","task":"Neural Architecture Search","dataset":"NAS-Bench-201, CIFAR-100","model":"DSNAS","rank_in_archive_order":40,"of":40,"metrics":{"Accuracy (Val)":"31.01"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-201","task":"Neural Architecture Search","dataset":"NAS-Bench-201, ImageNet-16-120","model":"DSNAS","rank_in_archive_order":48,"of":49,"metrics":{"Accuracy (Val)":"41.07"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.09128","atlas_url":"https://app.syntology.ai/?focus=2002.09128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09128"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SNAS-Series/SNAS-Series","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a1017b49bacb3e1a","entry":"init_dist","repo":"SNAS-Series/SNAS-Series","repo_kind":"official","path":"SNAS/dist_util_torch.py","file_url":"https://github.com/SNAS-Series/SNAS-Series/blob/HEAD/SNAS/dist_util_torch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1017b49bacb3e1a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}