{"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/maxup-a-simple-way-to-improve-generalization","title":"MaxUp: A Simple Way to Improve Generalization of Neural Network Training","arxiv_id":"2002.09024","date":"2020-02-20","proceeding":null,"authors":["Chengyue Gong","Tongzheng Ren","Mao Ye","Qiang Liu"],"abstract":"We propose \\emph{MaxUp}, an embarrassingly simple, highly effective technique for improving the generalization performance of machine learning models, especially deep neural networks. The idea is to generate a set of augmented data with some random perturbations or transforms and minimize the maximum, or worst case loss over the augmented data. By doing so, we implicitly introduce a smoothness or robustness regularization against the random perturbations, and hence improve the generation performance. For example, in the case of Gaussian perturbation, \\emph{MaxUp} is asymptotically equivalent to using the gradient norm of the loss as a penalty to encourage smoothness. We test \\emph{MaxUp} on a range of tasks, including image classification, language modeling, and adversarial certification, on which \\emph{MaxUp} consistently outperforms the existing best baseline methods, without introducing substantial computational overhead. In particular, we improve ImageNet classification from the state-of-the-art top-1 accuracy $85.5\\%$ without extra data to $85.8\\%$. Code will be released soon.","url_abs":"https://arxiv.org/abs/2002.09024v1","url_pdf":"https://arxiv.org/pdf/2002.09024v1.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":"maxup-a-simple-way-to-improve-generalization","repo_url":"https://github.com/Yunodo/maxup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"awd-lstm","method_name":"AWD-LSTM"},{"method_slug":"activation-regularization","method_name":"Activation Regularization"},{"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":"cutmix","method_name":"CutMix"},{"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":"dropconnect","method_name":"DropConnect"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"efficientnet","method_name":"EfficientNet"},{"method_slug":"embedding-dropout","method_name":"Embedding Dropout"},{"method_slug":"fixres","method_name":"FixRes"},{"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":"lstm","method_name":"LSTM"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"maxup","method_name":"MaxUp"},{"method_slug":"nt-asgd","method_name":"NT-ASGD"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"proxylessnet-cpu","method_name":"ProxylessNet-CPU"},{"method_slug":"proxylessnet-gpu","method_name":"ProxylessNet-GPU"},{"method_slug":"proxylessnet-mobile","method_name":"ProxylessNet-Mobile"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"randomhorizontalflip","method_name":"Random Horizontal Flip"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"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":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"temporal-activation-regularization","method_name":"Temporal Activation Regularization"},{"method_slug":"test","method_name":"Test"},{"method_slug":"variational-dropout","method_name":"Variational Dropout"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"weight-tying","method_name":"Weight Tying"}],"datasets_introduced":[],"methods_introduced":[{"slug":"maxup","name":"MaxUp","full_name":"MaxUp"}],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Fix-EfficientNet-B8 (MaxUp + CutMix)","rank_in_archive_order":194,"of":1060,"metrics":{"Number of params":"87.42M","Top 1 Accuracy":"85.8%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2002.09024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09024"}},"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/Yunodo/maxup","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"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":"6b99da07c845642e","entry":"MaxUp","repo":"Yunodo/maxup","repo_kind":"listed","path":"maxup/maxup.py","file_url":"https://github.com/Yunodo/maxup/blob/HEAD/maxup/maxup.py","link_basis":"first_harvest_node","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":"6b99da07c845642e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}