{"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":"/paper/revisiting-resnets-improved-training-and","title":"Revisiting ResNets: Improved Training and Scaling Strategies","arxiv_id":"2103.07579","date":"2021-03-13","proceeding":"NeurIPS 2021 12","authors":["Irwan Bello","William Fedus","Xianzhi Du","Ekin D. Cubuk","Aravind Srinivas","Tsung-Yi Lin","Jonathon Shlens","Barret Zoph"],"abstract":"Novel computer vision architectures monopolize the spotlight, but the impact of the model architecture is often conflated with simultaneous changes to training methodology and scaling strategies. Our work revisits the canonical ResNet (He et al., 2015) and studies these three aspects in an effort to disentangle them. Perhaps surprisingly, we find that training and scaling strategies may matter more than architectural changes, and further, that the resulting ResNets match recent state-of-the-art models. We show that the best performing scaling strategy depends on the training regime and offer two new scaling strategies: (1) scale model depth in regimes where overfitting can occur (width scaling is preferable otherwise); (2) increase image resolution more slowly than previously recommended (Tan & Le, 2019). Using improved training and scaling strategies, we design a family of ResNet architectures, ResNet-RS, which are 1.7x - 2.7x faster than EfficientNets on TPUs, while achieving similar accuracies on ImageNet. In a large-scale semi-supervised learning setup, ResNet-RS achieves 86.2% top-1 ImageNet accuracy, while being 4.7x faster than EfficientNet NoisyStudent. The training techniques improve transfer performance on a suite of downstream tasks (rivaling state-of-the-art self-supervised algorithms) and extend to video classification on Kinetics-400. We recommend practitioners use these simple revised ResNets as baselines for future research.","url_abs":"https://arxiv.org/abs/2103.07579v1","url_pdf":"https://arxiv.org/pdf/2103.07579v1.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":"revisiting-resnets-improved-training-and","repo_url":"https://github.com/tensorflow/tpu/tree/master/models/official/resnet/resnet_rs","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"revisiting-resnets-improved-training-and","repo_url":"https://github.com/nachiket273/pytorch_resnet_rs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"revisiting-resnets-improved-training-and","repo_url":"https://github.com/rwightman/pytorch-image-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"document-image-classification","task_name":"Document Image Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"semantic-object-interaction-classification","task_name":"Semantic Object Interaction Classification"},{"task_slug":"video-classification","task_name":"Video 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":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"efficientnet","method_name":"EfficientNet"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"resnet-d","method_name":"ResNet-D"},{"method_slug":"resnet-rs","method_name":"ResNet-RS"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"},{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"xavier-initialization","method_name":"Xavier Initialization"}],"datasets_introduced":[],"methods_introduced":[{"slug":"resnet-rs","name":"ResNet-RS","full_name":"ResNet-RS"}],"results":[{"leaderboard":"/sota/document-image-classification-on-aip","task":"Document Image Classification","dataset":"AIP","model":"ResNet-RS (ResNet-200 + RS training tricks)","rank_in_archive_order":1,"of":1,"metrics":{"Top 1 Accuracy - Verb":"83.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-RS-50 (160 image res)","rank_in_archive_order":322,"of":1060,"metrics":{"GFLOPs":"4.6","Number of params":"192M","Top 1 Accuracy":"84.4%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-RS-270 (256 image res)","rank_in_archive_order":384,"of":1060,"metrics":{"GFLOPs":"54","Top 1 Accuracy":"83.8%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-prima","task":"Image Classification","dataset":"PRImA","model":"ResNet-152 2x (RS training)","rank_in_archive_order":1,"of":1,"metrics":{"Percentage correct":"89.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.07579","atlas_url":"https://app.syntology.ai/?focus=2103.07579","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2103.07579"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.07579\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.07579"},"call":"get_concepts_for_paper(arxiv_id=\"2103.07579\")"}],"by_repo":[{"repo":"tensorflow/tpu","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2403.14715"],"harvested_for_calls":[{"arxiv_id":"2403.14715","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.14715"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.14715\")"}]},{"repo":"nachiket273/pytorch_resnet_rs","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1603.09382","1909.13719"],"harvested_for_calls":[{"arxiv_id":"1603.09382","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1603.09382"},"call":"get_harvested_code_for_paper(arxiv_id=\"1603.09382\")"},{"arxiv_id":"1909.13719","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.13719"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.13719\")"}]},{"repo":"rwightman/pytorch-image-models","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2006.08217"],"harvested_for_calls":[{"arxiv_id":"2006.08217","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.08217"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.08217\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c4f3b1c902c71dff3bd2db0e7309305bb00aca722d08262881c3be6549e21c4b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}