{"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":"/sota/neural-architecture-search-on-imagenet","task":{"name":"Neural Architecture Search","url":"/task/architecture-search","note":null},"dataset":{"name":"ImageNet","url":"/dataset/imagenet"},"category":"Methodology","categories":["Methodology"],"category_note":null,"description":"**Neural architecture search (NAS)** is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS essentially takes the process of a human manually tweaking a neural network and learning what works well, and automates this task to discover more complex architectures.\r\n\r\nImage Credit : [NAS with Reinforcement Learning](https://arxiv.org/abs/1611.01578)","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Top-1 Error Rate","Accuracy","Params","MACs","FLOPs"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Top-1 Error Rate":null,"Accuracy":"higher","Params":"lower","MACs":null,"FLOPs":"lower"}},"counts":{"rows":135,"rows_with_code":119,"rows_with_paper_page":133,"rows_dated":133,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DeepMAD-50M","metrics":{"Accuracy":"83.9","FLOPs":"8.7G","Params":"50M","Top-1 Error Rate":"16.1"},"uses_additional_data":false,"paper_date":"2023-03-05","paper":"/paper/deepmad-mathematical-architecture-design-for","paper_url":"https://arxiv.org/abs/2303.02165v3","paper_title":"DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network","code":"https://github.com/alibaba/lightweight-neural-architecture-search","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"ZenNAS (1.2ms)","metrics":{"Accuracy":"83.6","FLOPs":"22G","Params":"180M","Top-1 Error Rate":"16.4"},"uses_additional_data":false,"paper_date":"2021-02-01","paper":"/paper/zen-nas-a-zero-shot-nas-for-high-performance","paper_url":"https://arxiv.org/abs/2102.01063v4","paper_title":"Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition","code":"https://github.com/alibaba/lightweight-neural-architecture-search","n_code_links":2,"official":{"repos":["alibaba/lightweight-neural-architecture-search"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/zen-nas-a-zero-shot-nas-for-high-performance#ran","syntology_url":"https://syntology.ai/paper/2102.01063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.01063"}}}},{"rank_in_archive_order":3,"model":"GPUNet-D3","metrics":{"FLOPs":"15.6G","Params":"19M","Top-1 Error Rate":"16.4"},"uses_additional_data":false,"paper_date":"2022-04-26","paper":"/paper/gpunet-searching-the-deployable-convolution","paper_url":"https://arxiv.org/abs/2205.00841v1","paper_title":"GPUNet: Searching the Deployable Convolution Neural Networks for GPUs","code":"https://github.com/NVIDIA/DeepLearningExamples","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"GPUNet-D1","metrics":{"FLOPs":"3.66G","Params":"10.6M","Top-1 Error Rate":"17.5"},"uses_additional_data":false,"paper_date":"2022-04-26","paper":"/paper/gpunet-searching-the-deployable-convolution","paper_url":"https://arxiv.org/abs/2205.00841v1","paper_title":"GPUNet: Searching the Deployable Convolution Neural Networks for GPUs","code":"https://github.com/NVIDIA/DeepLearningExamples","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":5,"model":"FBNetV3-G","metrics":{"Accuracy":"82.3","MACs":"2.0G","Top-1 Error Rate":"17.7"},"uses_additional_data":false,"paper_date":"2020-06-03","paper":"/paper/fbnetv3-joint-architecture-recipe-search","paper_url":"https://arxiv.org/abs/2006.02049v3","paper_title":"FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"BossNet-T1+","metrics":{"Accuracy":"82.2","MACs":"10.5G","Top-1 Error Rate":"17.8"},"uses_additional_data":false,"paper_date":"2021-03-23","paper":"/paper/bossnas-exploring-hybrid-cnn-transformers","paper_url":"https://arxiv.org/abs/2103.12424v3","paper_title":"BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search","code":"https://github.com/changlin31/BossNAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"NASViT-A5","metrics":{"Accuracy":"81.8","FLOPs":"757M","Top-1 Error Rate":"18.2"},"uses_additional_data":false,"paper_date":"2021-09-29","paper":"/paper/nasvit-neural-architecture-search-for","paper_url":"https://openreview.net/forum?id=Qaw16njk6L","paper_title":"NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training","code":"https://github.com/facebookresearch/NASViT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"FBNetV5","metrics":{"FLOPs":"726M","Top-1 Error Rate":"18.2"},"uses_additional_data":false,"paper_date":"2021-11-19","paper":"/paper/fbnetv5-neural-architecture-search-for","paper_url":"https://arxiv.org/abs/2111.10007v3","paper_title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"FBNetV5-A-CLS","metrics":{"Accuracy":"81.7","FLOPs":"685M","Top-1 Error Rate":"18.3"},"uses_additional_data":false,"paper_date":"2021-11-19","paper":"/paper/fbnetv5-neural-architecture-search-for","paper_url":"https://arxiv.org/abs/2111.10007v3","paper_title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":10,"model":"NASViT-A4","metrics":{"Accuracy":"81.4","FLOPs":"591M","Top-1 Error Rate":"18.6"},"uses_additional_data":false,"paper_date":"2021-09-29","paper":"/paper/nasvit-neural-architecture-search-for","paper_url":"https://openreview.net/forum?id=Qaw16njk6L","paper_title":"NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training","code":"https://github.com/facebookresearch/NASViT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":11,"model":"NASViT-A3","metrics":{"Accuracy":"81.0","FLOPs":"528M","Top-1 Error Rate":"19.0"},"uses_additional_data":false,"paper_date":"2021-09-29","paper":"/paper/nasvit-neural-architecture-search-for","paper_url":"https://openreview.net/forum?id=Qaw16njk6L","paper_title":"NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training","code":"https://github.com/facebookresearch/NASViT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":12,"model":"AlphaNet-A6","metrics":{"Accuracy":"80.8","FLOPs":"709M","Top-1 Error Rate":"19.2"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/alphanet-improved-training-of-supernet-with","paper_url":"https://arxiv.org/abs/2102.07954v2","paper_title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":{"repos":["facebookresearch/AlphaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official","unlocated"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":15,"n_samples":31,"n_pointer_only_licence":31,"sample_list":"/paper/alphanet-improved-training-of-supernet-with#ran","syntology_url":"https://syntology.ai/paper/2102.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07954"}}}},{"rank_in_archive_order":13,"model":"UniNet-B0","metrics":{"FLOPs":"555M","Params":"11.5M","Top-1 Error Rate":"19.2"},"uses_additional_data":false,"paper_date":"2022-07-12","paper":"/paper/uninet-unified-architecture-search-with-1","paper_url":"https://arxiv.org/abs/2207.05420v2","paper_title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","code":"https://github.com/sense-x/tokenmix","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"AlphaNet-A5 (base)","metrics":{"Accuracy":"80.6","FLOPs":"596M","Top-1 Error Rate":"19.4"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/alphanet-improved-training-of-supernet-with","paper_url":"https://arxiv.org/abs/2102.07954v2","paper_title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":{"repos":["facebookresearch/AlphaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official","unlocated"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":15,"n_samples":31,"n_pointer_only_licence":31,"sample_list":"/paper/alphanet-improved-training-of-supernet-with#ran","syntology_url":"https://syntology.ai/paper/2102.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07954"}}}},{"rank_in_archive_order":15,"model":"NAT-M4","metrics":{"Accuracy":"80.5","MACs":"600M","Params":"9.1M","Top-1 Error Rate":"19.5"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"official":{"repos":["human-analysis/neural-architecture-transfer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/neural-architecture-transfer#ran","syntology_url":"https://syntology.ai/paper/2005.05859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05859"}}}},{"rank_in_archive_order":16,"model":"NASViT-A2","metrics":{"Accuracy":"80.5","FLOPs":"421M","Top-1 Error Rate":"19.5"},"uses_additional_data":false,"paper_date":"2021-09-29","paper":"/paper/nasvit-neural-architecture-search-for","paper_url":"https://openreview.net/forum?id=Qaw16njk6L","paper_title":"NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training","code":"https://github.com/facebookresearch/NASViT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"NSGANetV2-xl","metrics":{"Accuracy":"80.4","MACs":"593M","Params":"8.7M","Top-1 Error Rate":"19.6"},"uses_additional_data":false,"paper_date":"2020-07-20","paper":"/paper/nsganetv2-evolutionary-multi-objective","paper_url":"https://arxiv.org/abs/2007.10396v1","paper_title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","code":"https://github.com/mikelzc1990/nsganetv2","n_code_links":1,"official":{"repos":["mikelzc1990/nsganetv2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_samples":8,"n_pointer_only_licence":2,"sample_list":"/paper/nsganetv2-evolutionary-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2007.10396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10396"}}}},{"rank_in_archive_order":18,"model":"FBNetV3-E","metrics":{"Accuracy":"80.4","MACs":"752M","Top-1 Error Rate":"19.6"},"uses_additional_data":false,"paper_date":"2020-06-03","paper":"/paper/fbnetv3-joint-architecture-recipe-search","paper_url":"https://arxiv.org/abs/2006.02049v3","paper_title":"FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"AlphaNet-A5 (small)","metrics":{"Accuracy":"80.3","FLOPs":"491M","Top-1 Error Rate":"19.7"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/alphanet-improved-training-of-supernet-with","paper_url":"https://arxiv.org/abs/2102.07954v2","paper_title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":{"repos":["facebookresearch/AlphaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official","unlocated"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":15,"n_samples":31,"n_pointer_only_licence":31,"sample_list":"/paper/alphanet-improved-training-of-supernet-with#ran","syntology_url":"https://syntology.ai/paper/2102.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07954"}}}},{"rank_in_archive_order":20,"model":"ISyNet-N3","metrics":{"Top-1 Error Rate":"19.84"},"uses_additional_data":false,"paper_date":"2021-09-04","paper":"/paper/isynet-convolutional-neural-networks-design","paper_url":"https://arxiv.org/abs/2109.01932v2","paper_title":"ISyNet: Convolutional Neural Networks design for AI accelerator","code":"https://github.com/mindspore-ai/models/tree/master/research/cv/ISyNet","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"HardcoreNAS_E_KD","metrics":{"Accuracy":"80.1","MACs":"330M","Top-1 Error Rate":"19.9"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":22,"model":"AttentiveNAS-A5","metrics":{"Accuracy":"80.1","MACs":"491M","Top-1 Error Rate":"19.9"},"uses_additional_data":false,"paper_date":"2020-11-18","paper":"/paper/attentivenas-improving-neural-architecture","paper_url":"https://arxiv.org/abs/2011.09011v2","paper_title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"AlphaNet-A4","metrics":{"Accuracy":"80.0","FLOPs":"444M","Top-1 Error Rate":"20.0"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/alphanet-improved-training-of-supernet-with","paper_url":"https://arxiv.org/abs/2102.07954v2","paper_title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":{"repos":["facebookresearch/AlphaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official","unlocated"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":15,"n_samples":31,"n_pointer_only_licence":31,"sample_list":"/paper/alphanet-improved-training-of-supernet-with#ran","syntology_url":"https://syntology.ai/paper/2102.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07954"}}}},{"rank_in_archive_order":24,"model":"NAT-M3","metrics":{"Accuracy":"79.9","MACs":"490M","Params":"9.1M","Top-1 Error Rate":"20.1"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"official":{"repos":["human-analysis/neural-architecture-transfer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/neural-architecture-transfer#ran","syntology_url":"https://syntology.ai/paper/2005.05859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05859"}}}},{"rank_in_archive_order":25,"model":"AttentiveNAS-A4","metrics":{"Accuracy":"79.8","MACs":"444M","Top-1 Error Rate":"20.2"},"uses_additional_data":false,"paper_date":"2020-11-18","paper":"/paper/attentivenas-improving-neural-architecture","paper_url":"https://arxiv.org/abs/2011.09011v2","paper_title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"SEDONA (ResNet-152 Aux. Ens., K=4)","metrics":{"Top-1 Error Rate":"20.2"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/sedona-search-for-decoupled-neural-networks","paper_url":"https://openreview.net/forum?id=XLfdzwNKzch","paper_title":"SEDONA: Search for Decoupled Neural Networks toward Greedy Block-wise Learning","code":"https://github.com/mjpyeon/sedona","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"NASViT-A1","metrics":{"Accuracy":"79.7","FLOPs":"309M","Top-1 Error Rate":"20.3"},"uses_additional_data":false,"paper_date":"2021-09-29","paper":"/paper/nasvit-neural-architecture-search-for","paper_url":"https://openreview.net/forum?id=Qaw16njk6L","paper_title":"NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training","code":"https://github.com/facebookresearch/NASViT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":28,"model":"GPUNet-D0","metrics":{"FLOPs":"720M","Params":"6.2M","Top-1 Error Rate":"20.3"},"uses_additional_data":false,"paper_date":"2022-04-26","paper":"/paper/gpunet-searching-the-deployable-convolution","paper_url":"https://arxiv.org/abs/2205.00841v1","paper_title":"GPUNet: Searching the Deployable Convolution Neural Networks for GPUs","code":"https://github.com/NVIDIA/DeepLearningExamples","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"FBNetV3-C","metrics":{"Accuracy":"79.6","MACs":"544M","Top-1 Error Rate":"20.4"},"uses_additional_data":false,"paper_date":"2020-06-03","paper":"/paper/fbnetv3-joint-architecture-recipe-search","paper_url":"https://arxiv.org/abs/2006.02049v3","paper_title":"FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"BigNASModel-L","metrics":{"Accuracy":"79.5","MACs":"586M","Params":"6.4M","Top-1 Error Rate":"20.5"},"uses_additional_data":false,"paper_date":"2020-03-24","paper":"/paper/bignas-scaling-up-neural-architecture-search","paper_url":"https://arxiv.org/abs/2003.11142v3","paper_title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","code":"https://github.com/GAIA-vision/GAIA-cv","n_code_links":1,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/bignas-scaling-up-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/2003.11142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.11142"}}}},{"rank_in_archive_order":31,"model":"HardcoreNAS_D_KD","metrics":{"Accuracy":"79.5","MACs":"290M","Top-1 Error Rate":"20.5"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":32,"model":"ISyNet-N2","metrics":{"Top-1 Error Rate":"20.59"},"uses_additional_data":false,"paper_date":"2021-09-04","paper":"/paper/isynet-convolutional-neural-networks-design","paper_url":"https://arxiv.org/abs/2109.01932v2","paper_title":"ISyNet: Convolutional Neural Networks design for AI accelerator","code":"https://github.com/mindspore-ai/models/tree/master/research/cv/ISyNet","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"AlphaNet-A3","metrics":{"Accuracy":"79.4","FLOPs":"357M","Top-1 Error Rate":"20.6"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/alphanet-improved-training-of-supernet-with","paper_url":"https://arxiv.org/abs/2102.07954v2","paper_title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":{"repos":["facebookresearch/AlphaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official","unlocated"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":15,"n_samples":31,"n_pointer_only_licence":31,"sample_list":"/paper/alphanet-improved-training-of-supernet-with#ran","syntology_url":"https://syntology.ai/paper/2102.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07954"}}}},{"rank_in_archive_order":34,"model":"AlphaNet-A2","metrics":{"Accuracy":"79.2","FLOPs":"317M","Top-1 Error Rate":"20.8"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/alphanet-improved-training-of-supernet-with","paper_url":"https://arxiv.org/abs/2102.07954v2","paper_title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":{"repos":["facebookresearch/AlphaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official","unlocated"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":15,"n_samples":31,"n_pointer_only_licence":31,"sample_list":"/paper/alphanet-improved-training-of-supernet-with#ran","syntology_url":"https://syntology.ai/paper/2102.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07954"}}}},{"rank_in_archive_order":35,"model":"NSGANetV2-l","metrics":{"Accuracy":"79.1","MACs":"400M","Params":"8.0M","Top-1 Error Rate":"20.9"},"uses_additional_data":false,"paper_date":"2020-07-20","paper":"/paper/nsganetv2-evolutionary-multi-objective","paper_url":"https://arxiv.org/abs/2007.10396v1","paper_title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","code":"https://github.com/mikelzc1990/nsganetv2","n_code_links":1,"official":{"repos":["mikelzc1990/nsganetv2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_samples":8,"n_pointer_only_licence":2,"sample_list":"/paper/nsganetv2-evolutionary-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2007.10396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10396"}}}},{"rank_in_archive_order":36,"model":"AttentiveNAS-A3","metrics":{"Accuracy":"79.1","MACs":"357M","Top-1 Error Rate":"20.9"},"uses_additional_data":false,"paper_date":"2020-11-18","paper":"/paper/attentivenas-improving-neural-architecture","paper_url":"https://arxiv.org/abs/2011.09011v2","paper_title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"AlphaNet-A1","metrics":{"Accuracy":"79.0","FLOPs":"279M","Top-1 Error Rate":"21.0"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/alphanet-improved-training-of-supernet-with","paper_url":"https://arxiv.org/abs/2102.07954v2","paper_title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":{"repos":["facebookresearch/AlphaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official","unlocated"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":15,"n_samples":31,"n_pointer_only_licence":31,"sample_list":"/paper/alphanet-improved-training-of-supernet-with#ran","syntology_url":"https://syntology.ai/paper/2102.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07954"}}}},{"rank_in_archive_order":38,"model":"SEDONA (ResNet-152, K=4)","metrics":{"Top-1 Error Rate":"21.09"},"uses_additional_data":false,"paper_date":"2021-01-01","paper":"/paper/sedona-search-for-decoupled-neural-networks","paper_url":"https://openreview.net/forum?id=XLfdzwNKzch","paper_title":"SEDONA: Search for Decoupled Neural Networks toward Greedy Block-wise Learning","code":"https://github.com/mjpyeon/sedona","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"BigNASModel-M","metrics":{"Accuracy":"78.9","MACs":"418M","Params":"5.5M","Top-1 Error Rate":"21.1"},"uses_additional_data":false,"paper_date":"2020-03-24","paper":"/paper/bignas-scaling-up-neural-architecture-search","paper_url":"https://arxiv.org/abs/2003.11142v3","paper_title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","code":"https://github.com/GAIA-vision/GAIA-cv","n_code_links":1,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/bignas-scaling-up-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/2003.11142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.11142"}}}},{"rank_in_archive_order":40,"model":"HardcoreNAS_C_KD","metrics":{"Accuracy":"78.9","MACs":"270M","Top-1 Error Rate":"21.1"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":41,"model":"HardcoreNAS_B_KD","metrics":{"Accuracy":"78.8","MACs":"250M","Top-1 Error Rate":"21.2"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":42,"model":"AttentiveNAS-A2","metrics":{"Accuracy":"78.8","MACs":"317M","Top-1 Error Rate":"21.2"},"uses_additional_data":false,"paper_date":"2020-11-18","paper":"/paper/attentivenas-improving-neural-architecture","paper_url":"https://arxiv.org/abs/2011.09011v2","paper_title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"μDARTS","metrics":{"Accuracy":"78.76","Params":"602M","Top-1 Error Rate":"21.24"},"uses_additional_data":false,"paper_date":"2021-07-24","paper":"/paper/m-darts-model-uncertainty-aware","paper_url":"https://arxiv.org/abs/2107.11500v2","paper_title":"$μ$DARTS: Model Uncertainty-Aware Differentiable Architecture Search","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"NAT-M2","metrics":{"Accuracy":"78.6","MACs":"312M","Params":"7.7M","Top-1 Error Rate":"21.4"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"official":{"repos":["human-analysis/neural-architecture-transfer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/neural-architecture-transfer#ran","syntology_url":"https://syntology.ai/paper/2005.05859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05859"}}}},{"rank_in_archive_order":45,"model":"LayerNAS-600M","metrics":{"MACs":"627M","Params":"9.7M","Top-1 Error Rate":"21.4"},"uses_additional_data":false,"paper_date":"2023-04-23","paper":"/paper/layernas-neural-architecture-search-in","paper_url":"https://arxiv.org/abs/2304.11517v1","paper_title":"LayerNAS: Neural Architecture Search in Polynomial Complexity","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":46,"model":"ISyNet-N1-S3","metrics":{"Top-1 Error Rate":"21.45"},"uses_additional_data":false,"paper_date":"2021-09-04","paper":"/paper/isynet-convolutional-neural-networks-design","paper_url":"https://arxiv.org/abs/2109.01932v2","paper_title":"ISyNet: Convolutional Neural Networks design for AI accelerator","code":"https://github.com/mindspore-ai/models/tree/master/research/cv/ISyNet","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"DNA-d","metrics":{"Accuracy":"78.4","FLOPs":"611M","Params":"6.4M","Top-1 Error Rate":"21.6"},"uses_additional_data":false,"paper_date":"2019-11-29","paper":"/paper/blockwisely-supervised-neural-architecture","paper_url":"https://arxiv.org/abs/1911.13053v2","paper_title":"Blockwisely Supervised Neural Architecture Search with Knowledge Distillation","code":"https://github.com/changlin31/DNA","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"AttentiveNAS-A1","metrics":{"Accuracy":"78.4","MACs":"279M","Top-1 Error Rate":"21.6"},"uses_additional_data":false,"paper_date":"2020-11-18","paper":"/paper/attentivenas-improving-neural-architecture","paper_url":"https://arxiv.org/abs/2011.09011v2","paper_title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"NSGANetV2-m","metrics":{"Accuracy":"78.3","MACs":"312M","Params":"7.7M","Top-1 Error Rate":"21.7"},"uses_additional_data":false,"paper_date":"2020-07-20","paper":"/paper/nsganetv2-evolutionary-multi-objective","paper_url":"https://arxiv.org/abs/2007.10396v1","paper_title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","code":"https://github.com/mikelzc1990/nsganetv2","n_code_links":1,"official":{"repos":["mikelzc1990/nsganetv2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_samples":8,"n_pointer_only_licence":2,"sample_list":"/paper/nsganetv2-evolutionary-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2007.10396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10396"}}}},{"rank_in_archive_order":50,"model":"HardcoreNAS_A_KD","metrics":{"Accuracy":"78.3","MACs":"220M","Top-1 Error Rate":"21.7"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":51,"model":"NASViT-A0","metrics":{"Accuracy":"78.2","FLOPs":"208M","Top-1 Error Rate":"21.8"},"uses_additional_data":false,"paper_date":"2021-09-29","paper":"/paper/nasvit-neural-architecture-search-for","paper_url":"https://openreview.net/forum?id=Qaw16njk6L","paper_title":"NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training","code":"https://github.com/facebookresearch/NASViT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":52,"model":"HardcoreNAS_F","metrics":{"Accuracy":"78.1","MACs":"340M","Top-1 Error Rate":"21.9"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":53,"model":"FBNetV3-A","metrics":{"Accuracy":"78.0","MACs":"343M","Top-1 Error Rate":"22.0"},"uses_additional_data":false,"paper_date":"2020-06-03","paper":"/paper/fbnetv3-joint-architecture-recipe-search","paper_url":"https://arxiv.org/abs/2006.02049v3","paper_title":"FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"NoisyDARTS-A","metrics":{"Accuracy":"77.9","MACs":"449M","Params":"5.5M","Top-1 Error Rate":"22.1"},"uses_additional_data":false,"paper_date":"2020-05-07","paper":"/paper/noisy-differentiable-architecture-search","paper_url":"https://arxiv.org/abs/2005.03566v3","paper_title":"Noisy Differentiable Architecture Search","code":"https://github.com/xiaomi-automl/NoisyDARTS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":55,"model":"AlphaNet-A0","metrics":{"Accuracy":"77.9","FLOPs":"203M","Top-1 Error Rate":"22.1"},"uses_additional_data":false,"paper_date":"2021-02-16","paper":"/paper/alphanet-improved-training-of-supernet-with","paper_url":"https://arxiv.org/abs/2102.07954v2","paper_title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":{"repos":["facebookresearch/AlphaNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper","official","unlocated"]},"syntology":{"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":15,"n_samples":31,"n_pointer_only_licence":31,"sample_list":"/paper/alphanet-improved-training-of-supernet-with#ran","syntology_url":"https://syntology.ai/paper/2102.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07954"}}}},{"rank_in_archive_order":56,"model":"HardcoreNAS_E","metrics":{"Accuracy":"77.9","MACs":"330M","Top-1 Error Rate":"22.1"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":57,"model":"ISyNet-N1-S2","metrics":{"Top-1 Error Rate":"22.15"},"uses_additional_data":false,"paper_date":"2021-09-04","paper":"/paper/isynet-convolutional-neural-networks-design","paper_url":"https://arxiv.org/abs/2109.01932v2","paper_title":"ISyNet: Convolutional Neural Networks design for AI accelerator","code":"https://github.com/mindspore-ai/models/tree/master/research/cv/ISyNet","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"DNA-c","metrics":{"Accuracy":"77.8","FLOPs":"466M","Params":"5.3M","Top-1 Error Rate":"22.2"},"uses_additional_data":false,"paper_date":"2019-11-29","paper":"/paper/blockwisely-supervised-neural-architecture","paper_url":"https://arxiv.org/abs/1911.13053v2","paper_title":"Blockwisely Supervised Neural Architecture Search with Knowledge Distillation","code":"https://github.com/changlin31/DNA","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"ZenNAS (0.1ms)","metrics":{"Accuracy":"77.8","FLOPs":"1.7G","Params":"30.1","Top-1 Error Rate":"22.2"},"uses_additional_data":false,"paper_date":"2021-02-01","paper":"/paper/zen-nas-a-zero-shot-nas-for-high-performance","paper_url":"https://arxiv.org/abs/2102.01063v4","paper_title":"Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition","code":"https://github.com/alibaba/lightweight-neural-architecture-search","n_code_links":2,"official":{"repos":["alibaba/lightweight-neural-architecture-search"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/zen-nas-a-zero-shot-nas-for-high-performance#ran","syntology_url":"https://syntology.ai/paper/2102.01063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.01063"}}}},{"rank_in_archive_order":60,"model":"AutoNL-L","metrics":{"Accuracy":"77.7","Top-1 Error Rate":"22.3"},"uses_additional_data":false,"paper_date":"2020-04-04","paper":"/paper/neural-architecture-search-for-lightweight","paper_url":"https://arxiv.org/abs/2004.01961v1","paper_title":"Neural Architecture Search for Lightweight Non-Local Networks","code":"https://github.com/LiYingwei/AutoNL","n_code_links":2,"official":{"repos":["LiYingwei/AutoNL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/neural-architecture-search-for-lightweight#ran","syntology_url":"https://syntology.ai/paper/2004.01961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01961"}}}},{"rank_in_archive_order":61,"model":"AtomNAS-C+†","metrics":{"Accuracy":"77.6","MACs":"363M","Params":"5.9M","Top-1 Error Rate":"22.4"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/atomnas-fine-grained-end-to-end-neural-1","paper_url":"https://arxiv.org/abs/1912.09640v2","paper_title":"AtomNAS: Fine-Grained End-to-End Neural Architecture Search","code":"https://github.com/meijieru/AtomNAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"NAT-M1","metrics":{"Accuracy":"77.5","MACs":"225M","Params":"6.0M","Top-1 Error Rate":"22.5"},"uses_additional_data":false,"paper_date":"2020-05-12","paper":"/paper/neural-architecture-transfer","paper_url":"https://arxiv.org/abs/2005.05859v2","paper_title":"Neural Architecture Transfer","code":"https://github.com/human-analysis/neural-architecture-transfer","n_code_links":2,"official":{"repos":["human-analysis/neural-architecture-transfer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/neural-architecture-transfer#ran","syntology_url":"https://syntology.ai/paper/2005.05859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.05859"}}}},{"rank_in_archive_order":63,"model":"DNA-b","metrics":{"Accuracy":"77.5","FLOPs":"406M","Params":"4.9M","Top-1 Error Rate":"22.5"},"uses_additional_data":false,"paper_date":"2019-11-29","paper":"/paper/blockwisely-supervised-neural-architecture","paper_url":"https://arxiv.org/abs/1911.13053v2","paper_title":"Blockwisely Supervised Neural Architecture Search with Knowledge Distillation","code":"https://github.com/changlin31/DNA","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"NSGANetV2-s","metrics":{"Accuracy":"77.4","MACs":"225M","Params":"6.1M","Top-1 Error Rate":"22.6"},"uses_additional_data":false,"paper_date":"2020-07-20","paper":"/paper/nsganetv2-evolutionary-multi-objective","paper_url":"https://arxiv.org/abs/2007.10396v1","paper_title":"NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search","code":"https://github.com/mikelzc1990/nsganetv2","n_code_links":1,"official":{"repos":["mikelzc1990/nsganetv2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_samples":8,"n_pointer_only_licence":2,"sample_list":"/paper/nsganetv2-evolutionary-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2007.10396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10396"}}}},{"rank_in_archive_order":65,"model":"HardcoreNAS_D","metrics":{"Accuracy":"77.4","MACs":"290M","Top-1 Error Rate":"22.6"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":66,"model":"AttentiveNAS-A0","metrics":{"Accuracy":"77.3","MACs":"203M","Top-1 Error Rate":"22.7"},"uses_additional_data":false,"paper_date":"2020-11-18","paper":"/paper/attentivenas-improving-neural-architecture","paper_url":"https://arxiv.org/abs/2011.09011v2","paper_title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","code":"https://github.com/facebookresearch/AttentiveNAS","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"ISyNet-N1-S1","metrics":{"Top-1 Error Rate":"22.7"},"uses_additional_data":false,"paper_date":"2021-09-04","paper":"/paper/isynet-convolutional-neural-networks-design","paper_url":"https://arxiv.org/abs/2109.01932v2","paper_title":"ISyNet: Convolutional Neural Networks design for AI accelerator","code":"https://github.com/mindspore-ai/models/tree/master/research/cv/ISyNet","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":68,"model":"AtomNAS-B+†","metrics":{"Accuracy":"77.2","MACs":"329M","Params":"5.5M","Top-1 Error Rate":"22.8"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/atomnas-fine-grained-end-to-end-neural-1","paper_url":"https://arxiv.org/abs/1912.09640v2","paper_title":"AtomNAS: Fine-Grained End-to-End Neural Architecture Search","code":"https://github.com/meijieru/AtomNAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"FBNetV5-AR-CLS","metrics":{"Accuracy":"77.2","FLOPs":"215M","Top-1 Error Rate":"22.8"},"uses_additional_data":false,"paper_date":"2021-11-19","paper":"/paper/fbnetv5-neural-architecture-search-for","paper_url":"https://arxiv.org/abs/2111.10007v3","paper_title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":70,"model":"FBNetV2-L1","metrics":{"Accuracy":"77.2","MACs":"325M","Top-1 Error Rate":"22.8"},"uses_additional_data":false,"paper_date":"2020-04-12","paper":"/paper/fbnetv2-differentiable-neural-architecture","paper_url":"https://arxiv.org/abs/2004.05565v1","paper_title":"FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions","code":"https://github.com/facebookresearch/mobile-vision","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"FairDARTS-C","metrics":{"MACs":"386M","Top-1 Error Rate":"22.8"},"uses_additional_data":false,"paper_date":"2019-11-27","paper":"/paper/fair-darts-eliminating-unfair-advantages-in","paper_url":"https://arxiv.org/abs/1911.12126v4","paper_title":"Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search","code":"https://github.com/xiaomi-automl/fairdarts","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":72,"model":"GreedyNAS-A","metrics":{"Accuracy":"77.1","Params":"6.5M","Top-1 Error Rate":"22.9"},"uses_additional_data":false,"paper_date":"2020-03-25","paper":"/paper/greedynas-towards-fast-one-shot-nas-with","paper_url":"https://arxiv.org/abs/2003.11236v1","paper_title":"GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":73,"model":"DNA-a","metrics":{"Accuracy":"77.1","FLOPs":"348M","Params":"4.2M","Top-1 Error Rate":"22.9"},"uses_additional_data":false,"paper_date":"2019-11-29","paper":"/paper/blockwisely-supervised-neural-architecture","paper_url":"https://arxiv.org/abs/1911.13053v2","paper_title":"Blockwisely Supervised Neural Architecture Search with Knowledge Distillation","code":"https://github.com/changlin31/DNA","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"HardcoreNAS_C","metrics":{"Accuracy":"77.1","MACs":"270M","Top-1 Error Rate":"22.9"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":75,"model":"LayerNAS-300M","metrics":{"MACs":"322M","Params":"5.2M","Top-1 Error Rate":"22.9"},"uses_additional_data":false,"paper_date":"2023-04-23","paper":"/paper/layernas-neural-architecture-search-in","paper_url":"https://arxiv.org/abs/2304.11517v1","paper_title":"LayerNAS: Neural Architecture Search in Polynomial Complexity","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":76,"model":"SCARLET-A","metrics":{"Accuracy":"76.9","MACs":"365M","Params":"6.7M","Top-1 Error Rate":"23.1"},"uses_additional_data":false,"paper_date":"2019-08-16","paper":"/paper/scarletnas-bridging-the-gap-between","paper_url":"https://arxiv.org/abs/1908.06022v6","paper_title":"SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search","code":"https://github.com/xiaomi-automl/SCARLET-NAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"OFA w/ PS #75","metrics":{"Accuracy":"76.9","MACs":"230M","Top-1 Error Rate":"23.1"},"uses_additional_data":false,"paper_date":"2019-08-26","paper":"/paper/once-for-all-train-one-network-and-specialize","paper_url":"https://arxiv.org/abs/1908.09791v5","paper_title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","code":"https://github.com/mit-han-lab/once-for-all","n_code_links":10,"official":{"repos":["mit-han-lab/once-for-all"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":24,"n_constructed":0,"n_ran_checked":19,"n_instrument":5,"n_unverified":10,"n_samples":34,"n_pointer_only_licence":8,"sample_list":"/paper/once-for-all-train-one-network-and-specialize#ran","syntology_url":"https://syntology.ai/paper/1908.09791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09791"}}}},{"rank_in_archive_order":78,"model":"ISyNet-N1","metrics":{"Top-1 Error Rate":"23.16"},"uses_additional_data":false,"paper_date":"2021-09-04","paper":"/paper/isynet-convolutional-neural-networks-design","paper_url":"https://arxiv.org/abs/2109.01932v2","paper_title":"ISyNet: Convolutional Neural Networks design for AI accelerator","code":"https://github.com/mindspore-ai/models/tree/master/research/cv/ISyNet","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"GreedyNAS-B","metrics":{"Accuracy":"76.8","Params":"5.2M","Top-1 Error Rate":"23.2"},"uses_additional_data":false,"paper_date":"2020-03-25","paper":"/paper/greedynas-towards-fast-one-shot-nas-with","paper_url":"https://arxiv.org/abs/2003.11236v1","paper_title":"GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":80,"model":"MUXNet-l","metrics":{"Accuracy":"76.6","MACs":"318M","Params":"4.0M","Top-1 Error Rate":"23.4"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/muxconv-information-multiplexing-in","paper_url":"https://arxiv.org/abs/2003.13880v2","paper_title":"MUXConv: Information Multiplexing in Convolutional Neural Networks","code":"https://github.com/human-analysis/MUXConv","n_code_links":1,"official":{"repos":["human-analysis/MUXConv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/muxconv-information-multiplexing-in#ran","syntology_url":"https://syntology.ai/paper/2003.13880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13880"}}}},{"rank_in_archive_order":81,"model":"GBDT-NAS-3S","metrics":{"Accuracy":"76.5","MACs":"577M","Params":"6.4M","Top-1 Error Rate":"23.5"},"uses_additional_data":false,"paper_date":"2020-07-09","paper":"/paper/neural-architecture-search-with-gbdt","paper_url":"https://arxiv.org/abs/2007.04785v3","paper_title":"Accuracy Prediction with Non-neural Model for Neural Architecture Search","code":"https://github.com/renqianluo/GBDT-NAS","n_code_links":1,"official":{"repos":["renqianluo/GBDT-NAS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":1,"sample_list":"/paper/neural-architecture-search-with-gbdt#ran","syntology_url":"https://syntology.ai/paper/2007.04785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.04785"}}}},{"rank_in_archive_order":82,"model":"BigNASModel-S","metrics":{"Accuracy":"76.5","MACs":"242M","Params":"4.5M","Top-1 Error Rate":"23.5"},"uses_additional_data":false,"paper_date":"2020-03-24","paper":"/paper/bignas-scaling-up-neural-architecture-search","paper_url":"https://arxiv.org/abs/2003.11142v3","paper_title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","code":"https://github.com/GAIA-vision/GAIA-cv","n_code_links":1,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/bignas-scaling-up-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/2003.11142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.11142"}}}},{"rank_in_archive_order":83,"model":"SemiNAS","metrics":{"Accuracy":"76.5","Top-1 Error Rate":"23.5"},"uses_additional_data":false,"paper_date":"2020-02-24","paper":"/paper/semi-supervised-neural-architecture-search","paper_url":"https://arxiv.org/abs/2002.10389v4","paper_title":"Semi-Supervised Neural Architecture Search","code":"https://github.com/renqianluo/SemiNAS","n_code_links":2,"official":{"repos":["renqianluo/SemiNAS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/semi-supervised-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/2002.10389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10389"}}}},{"rank_in_archive_order":84,"model":"AutoNL-S","metrics":{"Accuracy":"76.5","Top-1 Error Rate":"23.5"},"uses_additional_data":false,"paper_date":"2020-04-04","paper":"/paper/neural-architecture-search-for-lightweight","paper_url":"https://arxiv.org/abs/2004.01961v1","paper_title":"Neural Architecture Search for Lightweight Non-Local Networks","code":"https://github.com/LiYingwei/AutoNL","n_code_links":2,"official":{"repos":["LiYingwei/AutoNL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/neural-architecture-search-for-lightweight#ran","syntology_url":"https://syntology.ai/paper/2004.01961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01961"}}}},{"rank_in_archive_order":85,"model":"HardcoreNAS_B","metrics":{"Accuracy":"76.5","MACs":"250M","Top-1 Error Rate":"23.5"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":86,"model":"SCARLET-B","metrics":{"Accuracy":"76.3","MACs":"329M","Params":"6.5M","Top-1 Error Rate":"23.7"},"uses_additional_data":false,"paper_date":"2019-08-16","paper":"/paper/scarletnas-bridging-the-gap-between","paper_url":"https://arxiv.org/abs/1908.06022v6","paper_title":"SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search","code":"https://github.com/xiaomi-automl/SCARLET-NAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":87,"model":"AtomNAS-A+†","metrics":{"Accuracy":"76.3","MACs":"260M","Params":"4.7M","Top-1 Error Rate":"23.7"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/atomnas-fine-grained-end-to-end-neural-1","paper_url":"https://arxiv.org/abs/1912.09640v2","paper_title":"AtomNAS: Fine-Grained End-to-End Neural Architecture Search","code":"https://github.com/meijieru/AtomNAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":88,"model":"DrNAS","metrics":{"Params":"5.7M","Top-1 Error Rate":"23.7"},"uses_additional_data":false,"paper_date":"2020-06-18","paper":"/paper/drnas-dirichlet-neural-architecture-search","paper_url":"https://arxiv.org/abs/2006.10355v4","paper_title":"DrNAS: Dirichlet Neural Architecture Search","code":"https://github.com/xiangning-chen/DrNAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"GreedyNAS-C","metrics":{"Accuracy":"76.2","Params":"4.7M","Top-1 Error Rate":"23.8"},"uses_additional_data":false,"paper_date":"2020-03-25","paper":"/paper/greedynas-towards-fast-one-shot-nas-with","paper_url":"https://arxiv.org/abs/2003.11236v1","paper_title":"GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":90,"model":"EEEA-Net-C2 (b=7) (our)","metrics":{"Accuracy":"76.2","Top-1 Error Rate":"23.8"},"uses_additional_data":false,"paper_date":"2021-08-13","paper":"/paper/eeea-net-an-early-exit-evolutionary-neural","paper_url":"https://arxiv.org/abs/2108.06156v1","paper_title":"EEEA-Net: An Early Exit Evolutionary Neural Architecture Search","code":"https://github.com/chakkritte/eeea-net","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":91,"model":"MSR-DARTS (CIFAR-10)","metrics":{"Accuracy":"76.1","MACs":"632M","Params":"5.6M","Top-1 Error Rate":"23.9"},"uses_additional_data":false,"paper_date":"2020-09-19","paper":"/paper/neural-architecture-search-using-stable-rank","paper_url":"https://arxiv.org/abs/2009.09209v2","paper_title":"MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":92,"model":"Shapley-NAS","metrics":{"MACs":"582M","Params":"5.4M","Top-1 Error Rate":"23.9"},"uses_additional_data":false,"paper_date":"2022-06-20","paper":"/paper/shapley-nas-discovering-operation-1","paper_url":"https://arxiv.org/abs/2206.09811v1","paper_title":"Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search","code":"https://github.com/euphoria16/shapley-nas","n_code_links":1,"official":{"repos":["euphoria16/shapley-nas"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/shapley-nas-discovering-operation-1#ran","syntology_url":"https://syntology.ai/paper/2206.09811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.09811"}}}},{"rank_in_archive_order":93,"model":"b-DARTS (CIFAR-10)","metrics":{"Top-1 Error Rate":"23.9"},"uses_additional_data":false,"paper_date":"2022-03-03","paper":"/paper/b-darts-beta-decay-regularization-for","paper_url":"https://arxiv.org/abs/2203.01665v2","paper_title":"$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search","code":"https://github.com/Sunshine-Ye/Beta-DARTS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":94,"model":"DenseNAS-Large","metrics":{"FLOPs":"479M","Top-1 Error Rate":"23.9"},"uses_additional_data":false,"paper_date":"2019-06-23","paper":"/paper/densely-connected-search-space-for-more","paper_url":"https://arxiv.org/abs/1906.09607v3","paper_title":"Densely Connected Search Space for More Flexible Neural Architecture Search","code":"https://github.com/JaminFong/DenseNAS","n_code_links":1,"official":{"repos":["JaminFong/DenseNAS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/densely-connected-search-space-for-more#ran","syntology_url":"https://syntology.ai/paper/1906.09607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.09607"}}}},{"rank_in_archive_order":95,"model":"sharpDARTS","metrics":{"Accuracy":"76.0","MACs":"950M","Params":"8.3M","Top-1 Error Rate":"24.0"},"uses_additional_data":false,"paper_date":"2019-03-23","paper":"/paper/sharpdarts-faster-and-more-accurate","paper_url":"http://arxiv.org/abs/1903.09900v1","paper_title":"sharpDARTS: Faster and More Accurate Differentiable Architecture Search","code":"https://github.com/ahundt/sharpDARTS","n_code_links":2,"official":{"repos":["ahundt/sharpDARTS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/sharpdarts-faster-and-more-accurate#ran","syntology_url":"https://syntology.ai/paper/1903.09900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.09900"}}}},{"rank_in_archive_order":96,"model":"FBNetV2-F4","metrics":{"Accuracy":"76.0","MACs":"238M","Top-1 Error Rate":"24.0"},"uses_additional_data":false,"paper_date":"2020-04-12","paper":"/paper/fbnetv2-differentiable-neural-architecture","paper_url":"https://arxiv.org/abs/2004.05565v1","paper_title":"FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions","code":"https://github.com/facebookresearch/mobile-vision","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"GAEA PC-DARTS","metrics":{"Params":"5.6","Top-1 Error Rate":"24"},"uses_additional_data":false,"paper_date":"2020-04-16","paper":"/paper/geometry-aware-gradient-algorithms-for-neural","paper_url":"https://arxiv.org/abs/2004.07802v5","paper_title":"Geometry-Aware Gradient Algorithms for Neural Architecture Search","code":"https://github.com/liamcli/gaea_release","n_code_links":1,"official":{"repos":["liamcli/gaea_release"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":12,"n_constructed":9,"n_ran_checked":11,"n_instrument":1,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":5,"sample_list":"/paper/geometry-aware-gradient-algorithms-for-neural#ran","syntology_url":"https://syntology.ai/paper/2004.07802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07802"}}}},{"rank_in_archive_order":98,"model":"GATES","metrics":{"Accuracy":"75.9","Params":"5.6M","Top-1 Error Rate":"24.1"},"uses_additional_data":false,"paper_date":"2020-04-04","paper":"/paper/a-generic-graph-based-neural-architecture","paper_url":"https://arxiv.org/abs/2004.01899v3","paper_title":"A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS","code":"https://github.com/walkerning/aw_nas","n_code_links":1,"official":{"repos":["walkerning/aw_nas"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/a-generic-graph-based-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/2004.01899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.01899"}}}},{"rank_in_archive_order":99,"model":"SGAS","metrics":{"Accuracy":"75.9","MACs":"598M","Params":"5.4M","Top-1 Error Rate":"24.1"},"uses_additional_data":false,"paper_date":"2019-11-30","paper":"/paper/sgas-sequential-greedy-architecture-search","paper_url":"https://arxiv.org/abs/1912.00195v2","paper_title":"SGAS: Sequential Greedy Architecture Search","code":"https://github.com/lightaime/sgas","n_code_links":1,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_samples":7,"n_pointer_only_licence":4,"sample_list":"/paper/sgas-sequential-greedy-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1912.00195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00195"}}}},{"rank_in_archive_order":100,"model":"DU-DARTS","metrics":{"Accuracy":"75.9","Params":"5.3M","Top-1 Error Rate":"24.1"},"uses_additional_data":false,"paper_date":"2021-11-23","paper":"/paper/du-darts-decreasing-the-uncertainty-of","paper_url":"https://www.bmvc2021-virtualconference.com/conference/papers/paper_0209.html","paper_title":"DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search","code":"https://github.com/ShunLu91/DU-DARTS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":101,"model":"HardcoreNAS_A","metrics":{"Accuracy":"75.9","MACs":"220M","Top-1 Error Rate":"24.1"},"uses_additional_data":false,"paper_date":"2021-02-23","paper":"/paper/hardcore-nas-hard-constrained-differentiable","paper_url":"https://arxiv.org/abs/2102.11646v1","paper_title":"HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search","code":"https://github.com/Alibaba-MIIL/HardCoReNAS","n_code_links":2,"official":{"repos":["Alibaba-MIIL/HardCoReNAS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/hardcore-nas-hard-constrained-differentiable#ran","syntology_url":"https://syntology.ai/paper/2102.11646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11646"}}}},{"rank_in_archive_order":102,"model":"PC-DARTS (ImageNet)","metrics":{"Accuracy":"75.8","MACs":"597M","Params":"5.3M","Top-1 Error Rate":"24.2"},"uses_additional_data":false,"paper_date":"2019-07-12","paper":"/paper/pc-darts-partial-channel-connections-for","paper_url":"https://arxiv.org/abs/1907.05737v4","paper_title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","code":"https://github.com/yuhuixu1993/PC-DARTS","n_code_links":8,"official":{"repos":["yuhuixu1993/PC-DARTS"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":1,"sample_list":"/paper/pc-darts-partial-channel-connections-for#ran","syntology_url":"https://syntology.ai/paper/1907.05737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.05737"}}}},{"rank_in_archive_order":103,"model":"SCARLET-C","metrics":{"Accuracy":"75.6","MACs":"280M","Params":"6.0M","Top-1 Error Rate":"24.4"},"uses_additional_data":false,"paper_date":"2019-08-16","paper":"/paper/scarletnas-bridging-the-gap-between","paper_url":"https://arxiv.org/abs/1908.06022v6","paper_title":"SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search","code":"https://github.com/xiaomi-automl/SCARLET-NAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":104,"model":"EvNAS-B","metrics":{"Accuracy":"75.6","MACs":"599","Params":"5.3","Top-1 Error Rate":"24.4"},"uses_additional_data":false,"paper_date":"2020-12-23","paper":"/paper/evolving-neural-architecture-using-one-shot","paper_url":"https://arxiv.org/abs/2012.12540v1","paper_title":"Evolving Neural Architecture Using One Shot Model","code":"https://github.com/nightstorm0909/EvNAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":105,"model":"EvNAS-A","metrics":{"Accuracy":"75.6","MACs":"570","Params":"5.1","Top-1 Error Rate":"24.4"},"uses_additional_data":false,"paper_date":"2020-12-23","paper":"/paper/evolving-neural-architecture-using-one-shot","paper_url":"https://arxiv.org/abs/2012.12540v1","paper_title":"Evolving Neural Architecture Using One Shot Model","code":"https://github.com/nightstorm0909/EvNAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":106,"model":"LayerNAS-220M","metrics":{"MACs":"229M","Params":"5.1M","Top-1 Error Rate":"24.4"},"uses_additional_data":false,"paper_date":"2023-04-23","paper":"/paper/layernas-neural-architecture-search-in","paper_url":"https://arxiv.org/abs/2304.11517v1","paper_title":"LayerNAS: Neural Architecture Search in Polynomial Complexity","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":107,"model":"AlphaX-1","metrics":{"Accuracy":"75.5","Params":"5.4M","Top-1 Error Rate":"24.5"},"uses_additional_data":false,"paper_date":"2019-03-26","paper":"/paper/alphax-exploring-neural-architectures-with-1","paper_url":"https://arxiv.org/abs/1903.11059v2","paper_title":"AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search","code":"https://github.com/linnanwang/AlphaX-NASBench101","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":108,"model":"ISyNet-N0","metrics":{"Top-1 Error Rate":"24.55"},"uses_additional_data":false,"paper_date":"2021-09-04","paper":"/paper/isynet-convolutional-neural-networks-design","paper_url":"https://arxiv.org/abs/2109.01932v2","paper_title":"ISyNet: Convolutional Neural Networks design for AI accelerator","code":"https://github.com/mindspore-ai/models/tree/master/research/cv/ISyNet","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":109,"model":"Evo-NAS","metrics":{"Accuracy":"75.43","Top-1 Error Rate":"24.57"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":110,"model":"FairNAS-A","metrics":{"Accuracy":"75.34","MACs":"388M","Params":"4.6M","Top-1 Error Rate":"24.7"},"uses_additional_data":false,"paper_date":"2019-07-03","paper":"/paper/fairnas-rethinking-evaluation-fairness-of","paper_url":"https://arxiv.org/abs/1907.01845v5","paper_title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","code":"https://github.com/xiaomi-automl/FairNAS","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":111,"model":"MUXNet-m","metrics":{"Accuracy":"75.3","MACs":"218M","Params":"3.4M","Top-1 Error Rate":"24.7"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/muxconv-information-multiplexing-in","paper_url":"https://arxiv.org/abs/2003.13880v2","paper_title":"MUXConv: Information Multiplexing in Convolutional Neural Networks","code":"https://github.com/human-analysis/MUXConv","n_code_links":1,"official":{"repos":["human-analysis/MUXConv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/muxconv-information-multiplexing-in#ran","syntology_url":"https://syntology.ai/paper/2003.13880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13880"}}}},{"rank_in_archive_order":112,"model":"iDARTS (ImageNet)","metrics":{"MACs":"568M","Params":"5.1M","Top-1 Error Rate":"24.7"},"uses_additional_data":false,"paper_date":"2021-08-25","paper":"/paper/idarts-improving-darts-by-node-normalization","paper_url":"https://arxiv.org/abs/2108.11014v1","paper_title":"iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":113,"model":"ProxylesNAS","metrics":{"Accuracy":"75.1","MACs":"581M","Params":"5.1M","Top-1 Error Rate":"24.9"},"uses_additional_data":false,"paper_date":"2018-12-02","paper":"/paper/proxylessnas-direct-neural-architecture","paper_url":"http://arxiv.org/abs/1812.00332v2","paper_title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","code":"https://github.com/osmr/imgclsmob","n_code_links":23,"official":{"repos":["MIT-HAN-LAB/ProxylessNAS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":14,"n_instrument":3,"n_unverified":10,"n_samples":27,"n_pointer_only_licence":4,"sample_list":"/paper/proxylessnas-direct-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/1812.00332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00332"}}}},{"rank_in_archive_order":114,"model":"FairNAS-B","metrics":{"Accuracy":"75.1","MACs":"345M","Params":"4.5M","Top-1 Error Rate":"24.9"},"uses_additional_data":false,"paper_date":"2019-07-03","paper":"/paper/fairnas-rethinking-evaluation-fairness-of","paper_url":"https://arxiv.org/abs/1907.01845v5","paper_title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","code":"https://github.com/xiaomi-automl/FairNAS","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":115,"model":"EvNAS-C","metrics":{"Accuracy":"74.9","MACs":"547","Params":"4.9","Top-1 Error Rate":"25.1"},"uses_additional_data":false,"paper_date":"2020-12-23","paper":"/paper/evolving-neural-architecture-using-one-shot","paper_url":"https://arxiv.org/abs/2012.12540v1","paper_title":"Evolving Neural Architecture Using One Shot Model","code":"https://github.com/nightstorm0909/EvNAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":116,"model":"SharpSepConvDARTS","metrics":{"Accuracy":"74.1","MACs":"573M","Params":"4.9M","Top-1 Error Rate":"25.1"},"uses_additional_data":false,"paper_date":"2019-03-23","paper":"/paper/sharpdarts-faster-and-more-accurate","paper_url":"http://arxiv.org/abs/1903.09900v1","paper_title":"sharpDARTS: Faster and More Accurate Differentiable Architecture Search","code":"https://github.com/ahundt/sharpDARTS","n_code_links":2,"official":{"repos":["ahundt/sharpDARTS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/sharpdarts-faster-and-more-accurate#ran","syntology_url":"https://syntology.ai/paper/1903.09900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.09900"}}}},{"rank_in_archive_order":117,"model":"iDARTS (CIFAR-10)","metrics":{"MACs":"578M","Params":"5.1M","Top-1 Error Rate":"25.2"},"uses_additional_data":false,"paper_date":"2021-08-25","paper":"/paper/idarts-improving-darts-by-node-normalization","paper_url":"https://arxiv.org/abs/2108.11014v1","paper_title":"iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":118,"model":"RandWire-WS (small)","metrics":{"FLOPs":"583M","Params":"5.6M","Top-1 Error Rate":"25.3"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/exploring-randomly-wired-neural-networks-for","paper_url":"http://arxiv.org/abs/1904.01569v2","paper_title":"Exploring Randomly Wired Neural Networks for Image Recognition","code":"https://github.com/facebookresearch/pycls","n_code_links":9,"official":null,"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":21,"n_samples":31,"n_pointer_only_licence":1,"sample_list":"/paper/exploring-randomly-wired-neural-networks-for#ran","syntology_url":"https://syntology.ai/paper/1904.01569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01569"}}}},{"rank_in_archive_order":119,"model":"FairNAS-C","metrics":{"Accuracy":"74.69","MACs":"321M","Params":"4.4M","Top-1 Error Rate":"25.4"},"uses_additional_data":false,"paper_date":"2019-07-03","paper":"/paper/fairnas-rethinking-evaluation-fairness-of","paper_url":"https://arxiv.org/abs/1907.01845v5","paper_title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","code":"https://github.com/xiaomi-automl/FairNAS","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":120,"model":"EEEA-Net-C1 (b=7) (our)","metrics":{"Accuracy":"74.3","Top-1 Error Rate":"25.7"},"uses_additional_data":false,"paper_date":"2021-08-13","paper":"/paper/eeea-net-an-early-exit-evolutionary-neural","paper_url":"https://arxiv.org/abs/2108.06156v1","paper_title":"EEEA-Net: An Early Exit Evolutionary Neural Architecture Search","code":"https://github.com/chakkritte/eeea-net","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":121,"model":"MemNAS","metrics":{"Accuracy":"74.1","Top-1 Error Rate":"25.9"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/memnas-memory-efficient-neural-architecture","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Liu_MemNAS_Memory-Efficient_Neural_Architecture_Search_With_Grow-Trim_Learning_CVPR_2020_paper.html","paper_title":"MemNAS: Memory-Efficient Neural Architecture Search With Grow-Trim Learning","code":"https://github.com/MemNAS/MemNAS","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":122,"model":"GDAS","metrics":{"Accuracy":"74.0","MACs":"581","Params":"5.3","Top-1 Error Rate":"26.0"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":123,"model":"NN-MASS-B","metrics":{"Accuracy":"73.3","FLOPs":"393M","MACs":"393M","Params":"3.7M","Top-1 Error Rate":"26.7"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/how-does-topology-of-neural-architectures","paper_url":"https://openaccess.thecvf.com/content/CVPR2021/html/Bhardwaj_How_Does_Topology_Influence_Gradient_Propagation_and_Model_Performance_of_CVPR_2021_paper.html","paper_title":"How does topology of neural architectures impact gradient propagation and model performance?","code":"https://github.com/SLDGroup/NN_Mass","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":124,"model":"DARTS","metrics":{"Accuracy":"73.3","MACs":"595M","Params":"4.9","Top-1 Error Rate":"26.7"},"uses_additional_data":false,"paper_date":"2018-06-24","paper":"/paper/darts-differentiable-architecture-search","paper_url":"http://arxiv.org/abs/1806.09055v2","paper_title":"DARTS: Differentiable Architecture Search","code":"https://github.com/google-research/google-research/tree/master/enas_lm","n_code_links":59,"official":{"repos":["quark0/darts"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"syntology":{"n_ran":74,"n_constructed":30,"n_ran_checked":59,"n_instrument":15,"n_unverified":82,"n_samples":156,"n_pointer_only_licence":54,"sample_list":"/paper/darts-differentiable-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1806.09055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.09055"}}}},{"rank_in_archive_order":125,"model":"FBNetV2-F3","metrics":{"Accuracy":"73.2","MACs":"126M","Top-1 Error Rate":"26.8"},"uses_additional_data":false,"paper_date":"2020-04-12","paper":"/paper/fbnetv2-differentiable-neural-architecture","paper_url":"https://arxiv.org/abs/2004.05565v1","paper_title":"FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions","code":"https://github.com/facebookresearch/mobile-vision","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":126,"model":"NN-MASS-A","metrics":{"Accuracy":"72.9","FLOPs":"200M","MACs":"200M","Params":"2.3M","Top-1 Error Rate":"27.1"},"uses_additional_data":false,"paper_date":"2021-06-16","paper":"/paper/how-does-topology-of-neural-architectures","paper_url":"https://openaccess.thecvf.com/content/CVPR2021/html/Bhardwaj_How_Does_Topology_Influence_Gradient_Propagation_and_Model_Performance_of_CVPR_2021_paper.html","paper_title":"How does topology of neural architectures impact gradient propagation and model performance?","code":"https://github.com/SLDGroup/NN_Mass","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":127,"model":"MUXNet-s","metrics":{"Accuracy":"71.6","MACs":"117M","Params":"2.4M","Top-1 Error Rate":"28.4"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/muxconv-information-multiplexing-in","paper_url":"https://arxiv.org/abs/2003.13880v2","paper_title":"MUXConv: Information Multiplexing in Convolutional Neural Networks","code":"https://github.com/human-analysis/MUXConv","n_code_links":1,"official":{"repos":["human-analysis/MUXConv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/muxconv-information-multiplexing-in#ran","syntology_url":"https://syntology.ai/paper/2003.13880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13880"}}}},{"rank_in_archive_order":128,"model":"NASGEP","metrics":{"Accuracy":"70.49","Top-1 Error Rate":"29.51"},"uses_additional_data":false,"paper_date":"2020-05-15","paper":"/paper/optimizing-neural-architecture-search-using","paper_url":"https://arxiv.org/abs/2005.07669v1","paper_title":"Optimizing Neural Architecture Search using Limited GPU Time in a Dynamic Search Space: A Gene Expression Programming Approach","code":"https://github.com/hieule88/geneNas","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":129,"model":"LayerNAS-60M","metrics":{"MACs":"61M","Params":"3.7M","Top-1 Error Rate":"31"},"uses_additional_data":false,"paper_date":"2023-04-23","paper":"/paper/layernas-neural-architecture-search-in","paper_url":"https://arxiv.org/abs/2304.11517v1","paper_title":"LayerNAS: Neural Architecture Search in Polynomial Complexity","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":130,"model":"FBNetV2-F1","metrics":{"Accuracy":"68.3","MACs":"56M","Top-1 Error Rate":"31.7"},"uses_additional_data":false,"paper_date":"2020-04-12","paper":"/paper/fbnetv2-differentiable-neural-architecture","paper_url":"https://arxiv.org/abs/2004.05565v1","paper_title":"FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions","code":"https://github.com/facebookresearch/mobile-vision","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":131,"model":"MUXNet-xs","metrics":{"Accuracy":"66.7","MACs":"66M","Params":"1.8M","Top-1 Error Rate":"33.3"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/muxconv-information-multiplexing-in","paper_url":"https://arxiv.org/abs/2003.13880v2","paper_title":"MUXConv: Information Multiplexing in Convolutional Neural Networks","code":"https://github.com/human-analysis/MUXConv","n_code_links":1,"official":{"repos":["human-analysis/MUXConv"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/muxconv-information-multiplexing-in#ran","syntology_url":"https://syntology.ai/paper/2003.13880","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13880"}}}},{"rank_in_archive_order":132,"model":"SPOS (ProxylessNAS (GPU) latency)","metrics":{"Accuracy":"75.3","MACs":"465M"},"uses_additional_data":false,"paper_date":"2019-03-31","paper":"/paper/single-path-one-shot-neural-architecture","paper_url":"https://arxiv.org/abs/1904.00420v4","paper_title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","code":"https://github.com/open-mmlab/mmrazor","n_code_links":6,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":3,"sample_list":"/paper/single-path-one-shot-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/1904.00420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00420"}}}},{"rank_in_archive_order":133,"model":"SPOS (FBNet-C latency)","metrics":{"Accuracy":"75.1","MACs":"375M"},"uses_additional_data":false,"paper_date":"2019-03-31","paper":"/paper/single-path-one-shot-neural-architecture","paper_url":"https://arxiv.org/abs/1904.00420v4","paper_title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","code":"https://github.com/open-mmlab/mmrazor","n_code_links":6,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":3,"sample_list":"/paper/single-path-one-shot-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/1904.00420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00420"}}}},{"rank_in_archive_order":134,"model":"SPOS (block search + channel search)","metrics":{"Accuracy":"74.7","MACs":"328M"},"uses_additional_data":false,"paper_date":"2019-03-31","paper":"/paper/single-path-one-shot-neural-architecture","paper_url":"https://arxiv.org/abs/1904.00420v4","paper_title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","code":"https://github.com/open-mmlab/mmrazor","n_code_links":6,"official":null,"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":3,"sample_list":"/paper/single-path-one-shot-neural-architecture#ran","syntology_url":"https://syntology.ai/paper/1904.00420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00420"}}}},{"rank_in_archive_order":135,"model":"PNAS","metrics":{"Params":"5.1"},"uses_additional_data":false,"paper_date":"2017-12-02","paper":"/paper/progressive-neural-architecture-search","paper_url":"http://arxiv.org/abs/1712.00559v3","paper_title":"Progressive Neural Architecture Search","code":"https://github.com/tensorflow/models/tree/master/research/deeplab","n_code_links":18,"official":{"repos":["chenxi116/PNASNet.TF","tensorflow/models","chenxi116/PNASNet.pytorch"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2,"sample_list":"/paper/progressive-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1712.00559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.00559"}}}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 147 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,482 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 2 proposed a result; of those 2, 1 gave no cell that passed the extractor's own checks, 1 was rejected by the independent check, 0 await a verdict and 0 were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":135,"metric_columns":5,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1482,"candidates":147,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":2,"no_cell_passed_checks":1,"rejected_by_independent_check":1,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; 2 newer papers judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":2,"shown_on_page":2,"no_cell_split":{"no_cell_passed_checks_in_ledger":1,"rows_refused_by_rule":1,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2609.23087","outcome":"rejected","reason":null},{"arxiv_id":"2605.07378","outcome":"refused_by_rule","reason":"the model gave no value to check against the cell; the column header qualifies the metric in a way the leaderboard does not"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":56,"rows_with_any_sample_ran":51,"rows_with_a_run_with_no_instrument_failure":41,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":48,"rows_whose_official_repository_has_a_sample_that_ran":39,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":23,"rows_community_repositories_only":1,"rows_runs_from_other_or_unrecorded_repositories":2,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":23,"distinct_papers_with_any_sample_ran":21,"distinct_papers_with_a_run_with_no_instrument_failure":16,"samples_over_distinct_papers":{"n_ran":200,"n_constructed":39,"n_ran_checked":158,"n_instrument":42,"n_unverified":168,"n_samples":368,"n_pointer_only_licence":128,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":375,"n_constructed":39,"n_ran_checked":288,"n_instrument":87,"n_unverified":338,"n_samples":713,"n_pointer_only_licence":378,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"970566e58334ac1c05be4381a64d98346808392623cee8638a200d07a8bf9010","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}