{"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/resnet-strikes-back-an-improved-training","title":"ResNet strikes back: An improved training procedure in timm","arxiv_id":"2110.00476","date":"2021-10-01","proceeding":"NeurIPS Workshop ImageNet_PPF 2021 12","authors":["Ross Wightman","Hugo Touvron","Hervé Jégou"],"abstract":"The influential Residual Networks designed by He et al. remain the gold-standard architecture in numerous scientific publications. They typically serve as the default architecture in studies, or as baselines when new architectures are proposed. Yet there has been significant progress on best practices for training neural networks since the inception of the ResNet architecture in 2015. Novel optimization & data-augmentation have increased the effectiveness of the training recipes. In this paper, we re-evaluate the performance of the vanilla ResNet-50 when trained with a procedure that integrates such advances. We share competitive training settings and pre-trained models in the timm open-source library, with the hope that they will serve as better baselines for future work. For instance, with our more demanding training setting, a vanilla ResNet-50 reaches 80.4% top-1 accuracy at resolution 224x224 on ImageNet-val without extra data or distillation. We also report the performance achieved with popular models with our training procedure.","url_abs":"https://arxiv.org/abs/2110.00476v1","url_pdf":"https://arxiv.org/pdf/2110.00476v1.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":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/eshoyuan/taop2021-3rd-solution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/hunto/dist_kd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/jayroxis/ordering-in-graph-generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC0-1.0"}},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/open-mmlab/mmclassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/samsungsailmontreal/ghn3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/shinya7y/UniverseNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/sithu31296/semantic-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/Mind23-2/MindCode-4/tree/main/resnet_ipl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/Westlake-AI/openmixup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/code-implementation1/Code9/tree/main/resnest","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/james77777778/keras-image-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"resnet-strikes-back-an-improved-training","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-3/resnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"fine-grained-image-classification","task_name":"Fine-Grained Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"medical-image-classification","task_name":"Medical Image Classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/classification-on-indl","task":"Classification","dataset":"InDL","model":"ResNetV2_50","rank_in_archive_order":8,"of":9,"metrics":{"Average Recall":"88.08%"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-vizwiz","task":"Domain Generalization","dataset":"VizWiz-Classification","model":"ResNet-50 (gn)","rank_in_archive_order":9,"of":90,"metrics":{"Accuracy - All Images":"48.9","Accuracy - Clean Images":"44.4","Accuracy - Corrupted Images":"39.1"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-oxford","task":"Fine-Grained Image Classification","dataset":"Oxford 102 Flowers","model":"ResNet50 (A1)","rank_in_archive_order":15,"of":25,"metrics":{"Accuracy":"97.9%","FLOPS":"4.1","PARAMS":"24M"},"uses_additional_data":false},{"leaderboard":"/sota/fine-grained-image-classification-on-stanford","task":"Fine-Grained Image Classification","dataset":"Stanford Cars","model":"ResNet50 (A1)","rank_in_archive_order":71,"of":83,"metrics":{"Accuracy":"92.7%","FLOPS":"4.1B","PARAMS":"24M"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNet50 (A1)","rank_in_archive_order":47,"of":265,"metrics":{"Percentage correct":"98.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"cvpr_class","rank_in_archive_order":233,"of":265,"metrics":{"Percentage correct":"85.28"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ResNet50 (A1)","rank_in_archive_order":49,"of":211,"metrics":{"PARAMS":"25M","Percentage correct":"86.9"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-flowers-102","task":"Image Classification","dataset":"Flowers-102","model":"ResNet50 (A1)","rank_in_archive_order":30,"of":52,"metrics":{"Accuracy":"97.9","FLOPS":"4.1","PARAMS":"25M"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-152 (A2 + reg)","rank_in_archive_order":540,"of":1060,"metrics":{"Number of params":"60.2M","Top 1 Accuracy":"82.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-152 (A2)","rank_in_archive_order":610,"of":1060,"metrics":{"Number of params":"60.2M","Top 1 Accuracy":"81.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"DeiT-S (T2)","rank_in_archive_order":704,"of":1060,"metrics":{"Number of params":"22M","Top 1 Accuracy":"80.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet50 (A1)","rank_in_archive_order":705,"of":1060,"metrics":{"Number of params":"25M","Top 1 Accuracy":"80.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet50 (A3)","rank_in_archive_order":854,"of":1060,"metrics":{"Number of params":"25M","Top 1 Accuracy":"78.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-real","task":"Image Classification","dataset":"ImageNet ReaL","model":"ResNet50 (A1)","rank_in_archive_order":39,"of":57,"metrics":{"Accuracy":"85.7%","Params":"25M"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-v2","task":"Image Classification","dataset":"ImageNet V2","model":"ResNet50 (A1)","rank_in_archive_order":28,"of":33,"metrics":{"Top 1 Accuracy":"68.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2019","task":"Image Classification","dataset":"iNaturalist 2019","model":"ResNet50 (A2)","rank_in_archive_order":14,"of":22,"metrics":{"Top-1 Accuracy":"75.0"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-classification-on-nct-crc-he","task":"Medical Image Classification","dataset":"NCT-CRC-HE-100K","model":"ResNeXt-50-32x4d","rank_in_archive_order":2,"of":7,"metrics":{"Accuracy (%)":"95.46","F1-Score":"97.46","Precision":"99.91","Specificity":"99.43"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2110.00476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00476"}},"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/rwightman/pytorch-image-models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Westlake-AI/openmixup","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jayroxis/ordering-in-graph-generation","reach":{"status":"ok","spdx":"CC0-1.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/james77777778/keras-image-models","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/code-implementation1/Code9/tree/main/resnest","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mind23-2/MindCode-4/tree/main/resnet_ipl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/samsungsailmontreal/ghn3","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmdetection","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/open-mmlab/mmclassification","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/University/tree/main/model-3/resnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hunto/dist_kd","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eshoyuan/taop2021-3rd-solution","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sithu31296/semantic-segmentation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shinya7y/UniverseNet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f8b11070de02f39b","entry":"build_model","repo":"jayroxis/ordering-in-graph-generation","repo_kind":"listed","path":"model/misc.py","file_url":"https://github.com/jayroxis/ordering-in-graph-generation/blob/HEAD/model/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f8b11070de02f39b"}},{"code_sha256_prefix":"00c7a8890d7c5be6","entry":"build_module_registry","repo":"jayroxis/ordering-in-graph-generation","repo_kind":"listed","path":"model/misc.py","file_url":"https://github.com/jayroxis/ordering-in-graph-generation/blob/HEAD/model/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"00c7a8890d7c5be6"}},{"code_sha256_prefix":"35244ec766970e38","entry":"build_partial_class","repo":"jayroxis/ordering-in-graph-generation","repo_kind":"listed","path":"model/misc.py","file_url":"https://github.com/jayroxis/ordering-in-graph-generation/blob/HEAD/model/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"35244ec766970e38"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}