{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lets-keep-it-simple-using-simple","title":"Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures","arxiv_id":"1608.06037","date":"2016-08-22","proceeding":null,"authors":["Seyyed Hossein Hasanpour","Mohammad Rouhani","Mohsen Fayyaz","Mohammad Sabokrou"],"abstract":"Major winning Convolutional Neural Networks (CNNs), such as AlexNet, VGGNet, ResNet, GoogleNet, include tens to hundreds of millions of parameters, which impose considerable computation and memory overhead. This limits their practical use for training, optimization and memory efficiency. On the contrary, light-weight architectures, being proposed to address this issue, mainly suffer from low accuracy. These inefficiencies mostly stem from following an ad hoc procedure. We propose a simple architecture, called SimpleNet, based on a set of designing principles, with which we empirically show, a well-crafted yet simple and reasonably deep architecture can perform on par with deeper and more complex architectures. SimpleNet provides a good tradeoff between the computation/memory efficiency and the accuracy. Our simple 13-layer architecture outperforms most of the deeper and complex architectures to date such as VGGNet, ResNet, and GoogleNet on several well-known benchmarks while having 2 to 25 times fewer number of parameters and operations. This makes it very handy for embedded systems or systems with computational and memory limitations. We achieved state-of-the-art result on CIFAR10 outperforming several heavier architectures, near state of the art on MNIST and competitive results on CIFAR100 and SVHN. We also outperformed the much larger and deeper architectures such as VGGNet and popular variants of ResNets among others on the ImageNet dataset. Models are made available at: https://github.com/Coderx7/SimpleNet","url_abs":"https://arxiv.org/abs/1608.06037v8","url_pdf":"https://arxiv.org/pdf/1608.06037v8.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lets-keep-it-simple-using-simple","repo_url":"https://github.com/Coderx7/SimpleNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lets-keep-it-simple-using-simple","repo_url":"https://github.com/Coderx7/SimpleNet_Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"lets-keep-it-simple-using-simple","repo_url":"https://github.com/JavierAntoran/moby_dick","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lets-keep-it-simple-using-simple","repo_url":"https://github.com/JavierAntoran/moby_dick_whale_audio_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lets-keep-it-simple-using-simple","repo_url":"https://github.com/JavierAntoran/moby_dick_whale_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lets-keep-it-simple-using-simple","repo_url":"https://github.com/dorlivne/simple_net_pruning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"lets-keep-it-simple-using-simple","repo_url":"https://github.com/luckymouse0/SimpleNet-TF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"lets-keep-it-simple-using-simple","repo_url":"https://github.com/pdoyle5000/simple_net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"lets-keep-it-simple-using-simple","repo_url":"https://github.com/zhuoyang125/simple_classifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"simplenet","method_name":"SimpleNet"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"simplenet","name":"SimpleNet","full_name":"SimpleNet"}],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"SimpleNetv1","rank_in_archive_order":132,"of":265,"metrics":{"Percentage correct":"95.51"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"SimpleNetv1","rank_in_archive_order":138,"of":211,"metrics":{"Percentage correct":"78.37"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SimpleNetV1-9m-correct-labels","rank_in_archive_order":652,"of":1060,"metrics":{"Number of params":"9.5M","Top 1 Accuracy":"81.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SimpleNetV1-5m-correct-labels","rank_in_archive_order":773,"of":1060,"metrics":{"Number of params":"5.7M","Top 1 Accuracy":"79.12"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SimpleNetV1-small-075-correct-labels","rank_in_archive_order":941,"of":1060,"metrics":{"Number of params":"3M","Top 1 Accuracy":"75.66"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SimpleNetV1-9m","rank_in_archive_order":978,"of":1060,"metrics":{"Number of params":"9.5M","Top 1 Accuracy":"74.17"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SimpleNetV1-5m","rank_in_archive_order":1004,"of":1060,"metrics":{"Number of params":"5.7M","Top 1 Accuracy":"71.94"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SimpleNetV1-small-05-correct-labels","rank_in_archive_order":1030,"of":1060,"metrics":{"Number of params":"1.5M","Top 1 Accuracy":"69.11"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SimpleNetV1-small-075","rank_in_archive_order":1035,"of":1060,"metrics":{"Number of params":"3M","Top 1 Accuracy":"68.15"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"SimpleNetV1-small-05","rank_in_archive_order":1051,"of":1060,"metrics":{"Number of params":"1.5M","Top 1 Accuracy":"61.52"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"SimpleNetv1","rank_in_archive_order":11,"of":81,"metrics":{"Percentage error":"0.25"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.06037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.06037"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Coderx7/SimpleNet_Pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Coderx7/SimpleNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhuoyang125/simple_classifier","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pdoyle5000/simple_net","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dorlivne/simple_net_pruning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JavierAntoran/moby_dick_whale_audio_detection","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/luckymouse0/SimpleNet-TF","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JavierAntoran/moby_dick_whale_detection","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JavierAntoran/moby_dick","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":8},"by_repo_kind":{"listed":{"samples":11,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a4e6e7d660e9dc5f","entry":"simplenet","repo":"Coderx7/SimpleNet_Pytorch","repo_kind":"listed","path":"cifar/models/simplenet.py","file_url":"https://github.com/Coderx7/SimpleNet_Pytorch/blob/HEAD/cifar/models/simplenet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4e6e7d660e9dc5f"}},{"code_sha256_prefix":"76760ce0a901a24a","entry":"simplenet_cifar_310k","repo":"Coderx7/SimpleNet_Pytorch","repo_kind":"listed","path":"cifar/models/simplenet.py","file_url":"https://github.com/Coderx7/SimpleNet_Pytorch/blob/HEAD/cifar/models/simplenet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"76760ce0a901a24a"}},{"code_sha256_prefix":"d7ced00ade152828","entry":"simplenet_cifar_460k","repo":"Coderx7/SimpleNet_Pytorch","repo_kind":"listed","path":"cifar/models/simplenet.py","file_url":"https://github.com/Coderx7/SimpleNet_Pytorch/blob/HEAD/cifar/models/simplenet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7ced00ade152828"}},{"code_sha256_prefix":"05a762a121e5ad7d","entry":"gen_whalefb_mtx","repo":"JavierAntoran/moby_dick","repo_kind":"listed","path":"HMM_solution/format_data_wavelets_dct.py","file_url":"https://github.com/JavierAntoran/moby_dick/blob/HEAD/HMM_solution/format_data_wavelets_dct.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05a762a121e5ad7d"}},{"code_sha256_prefix":"e9fc42cebc176243","entry":"gen_whalefb_mtx","repo":"JavierAntoran/moby_dick","repo_kind":"listed","path":"NN_solution/format_data_250ms.py","file_url":"https://github.com/JavierAntoran/moby_dick/blob/HEAD/NN_solution/format_data_250ms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9fc42cebc176243"}},{"code_sha256_prefix":"6bb7eb96c72778f7","entry":"get_delta_mtx","repo":"JavierAntoran/moby_dick","repo_kind":"listed","path":"NN_solution/format_data_25ms.py","file_url":"https://github.com/JavierAntoran/moby_dick/blob/HEAD/NN_solution/format_data_25ms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bb7eb96c72778f7"}},{"code_sha256_prefix":"90e483b5f738c3e2","entry":"get_mtx_deltas","repo":"JavierAntoran/moby_dick","repo_kind":"listed","path":"HMM_solution/format_data_wavelets_dct.py","file_url":"https://github.com/JavierAntoran/moby_dick/blob/HEAD/HMM_solution/format_data_wavelets_dct.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90e483b5f738c3e2"}},{"code_sha256_prefix":"07abbcfa131c3e53","entry":"image_statistics","repo":"JavierAntoran/moby_dick","repo_kind":"listed","path":"template_boosting_solution/generate_templates.py","file_url":"https://github.com/JavierAntoran/moby_dick/blob/HEAD/template_boosting_solution/generate_templates.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"07abbcfa131c3e53"}},{"code_sha256_prefix":"2cb25e763e9871bb","entry":"windower","repo":"JavierAntoran/moby_dick","repo_kind":"listed","path":"HMM_solution/format_data_wavelets_dct.py","file_url":"https://github.com/JavierAntoran/moby_dick/blob/HEAD/HMM_solution/format_data_wavelets_dct.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2cb25e763e9871bb"}},{"code_sha256_prefix":"e228c13c8c5d69c2","entry":"windower","repo":"JavierAntoran/moby_dick","repo_kind":"listed","path":"NN_solution/format_data_250ms.py","file_url":"https://github.com/JavierAntoran/moby_dick/blob/HEAD/NN_solution/format_data_250ms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e228c13c8c5d69c2"}},{"code_sha256_prefix":"548cfa2028318949","entry":"windower","repo":"JavierAntoran/moby_dick","repo_kind":"listed","path":"NN_solution/format_data_25ms.py","file_url":"https://github.com/JavierAntoran/moby_dick/blob/HEAD/NN_solution/format_data_25ms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"548cfa2028318949"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}