{"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/zen-nas-a-zero-shot-nas-for-high-performance","title":"Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition","arxiv_id":"2102.01063","date":"2021-02-01","proceeding":null,"authors":["Ming Lin","Pichao Wang","Zhenhong Sun","Hesen Chen","Xiuyu Sun","Qi Qian","Hao Li","Rong Jin"],"abstract":"Accuracy predictor is a key component in Neural Architecture Search (NAS) for ranking architectures. Building a high-quality accuracy predictor usually costs enormous computation. To address this issue, instead of using an accuracy predictor, we propose a novel zero-shot index dubbed Zen-Score to rank the architectures. The Zen-Score represents the network expressivity and positively correlates with the model accuracy. The calculation of Zen-Score only takes a few forward inferences through a randomly initialized network, without training network parameters. Built upon the Zen-Score, we further propose a new NAS algorithm, termed as Zen-NAS, by maximizing the Zen-Score of the target network under given inference budgets. Within less than half GPU day, Zen-NAS is able to directly search high performance architectures in a data-free style. Comparing with previous NAS methods, the proposed Zen-NAS is magnitude times faster on multiple server-side and mobile-side GPU platforms with state-of-the-art accuracy on ImageNet. Our source code and pre-trained models are released on https://github.com/idstcv/ZenNAS.","url_abs":"https://arxiv.org/abs/2102.01063v4","url_pdf":"https://arxiv.org/pdf/2102.01063v4.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":"zen-nas-a-zero-shot-nas-for-high-performance","repo_url":"https://github.com/alibaba/lightweight-neural-architecture-search","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"zen-nas-a-zero-shot-nas-for-high-performance","repo_url":"https://github.com/idstcv/ZenNAS","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ZenNAS (0.8ms)","rank_in_archive_order":482,"of":1060,"metrics":{"GFLOPs":"13.9","Number of params":"183M","Top 1 Accuracy":"83.0%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ZenNet-400M-SE","rank_in_archive_order":855,"of":1060,"metrics":{"GFLOPs":"0.820","Number of params":"5.7M","Top 1 Accuracy":"78%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-cifar-10","task":"Neural Architecture Search","dataset":"CIFAR-10","model":"ZenNet-2.0M","rank_in_archive_order":19,"of":41,"metrics":{"FLOPS":"487M","Parameters":"2.0M","Top-1 Error Rate":"2.5%"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-cifar-100-1","task":"Neural Architecture Search","dataset":"CIFAR-100","model":"ZenNet-2.0M","rank_in_archive_order":7,"of":13,"metrics":{"FLOPS":"487M","PARAMS":"2.0M","Percentage Error":"15.6"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"ZenNAS (1.2ms)","rank_in_archive_order":2,"of":135,"metrics":{"Accuracy":"83.6","FLOPs":"22G","Params":"180M","Top-1 Error Rate":"16.4"},"uses_additional_data":false},{"leaderboard":"/sota/neural-architecture-search-on-imagenet","task":"Neural Architecture Search","dataset":"ImageNet","model":"ZenNAS (0.1ms)","rank_in_archive_order":59,"of":135,"metrics":{"Accuracy":"77.8","FLOPs":"1.7G","Params":"30.1","Top-1 Error Rate":"22.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.01063","atlas_url":"https://app.syntology.ai/?focus=2102.01063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.01063"}},"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":"deterministic:regex_extraction","url":"https://github.com/idstcv/ZenNAS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alibaba/lightweight-neural-architecture-search","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{},"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":2,"samples":[{"code_sha256_prefix":"866a541b53979f13","entry":"compute_nas_score","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"866a541b53979f13"}},{"code_sha256_prefix":"28d3ae653452ecdf","entry":"network_weight_gaussian_init","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"28d3ae653452ecdf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}