{"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/how-to-train-your-vit-data-augmentation-and","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","arxiv_id":"2106.10270","date":"2021-06-18","proceeding":null,"authors":["Andreas Steiner","Alexander Kolesnikov","Xiaohua Zhai","Ross Wightman","Jakob Uszkoreit","Lucas Beyer"],"abstract":"Vision Transformers (ViT) have been shown to attain highly competitive performance for a wide range of vision applications, such as image classification, object detection and semantic image segmentation. In comparison to convolutional neural networks, the Vision Transformer's weaker inductive bias is generally found to cause an increased reliance on model regularization or data augmentation (\"AugReg\" for short) when training on smaller training datasets. We conduct a systematic empirical study in order to better understand the interplay between the amount of training data, AugReg, model size and compute budget. As one result of this study we find that the combination of increased compute and AugReg can yield models with the same performance as models trained on an order of magnitude more training data: we train ViT models of various sizes on the public ImageNet-21k dataset which either match or outperform their counterparts trained on the larger, but not publicly available JFT-300M dataset.","url_abs":"https://arxiv.org/abs/2106.10270v2","url_pdf":"https://arxiv.org/pdf/2106.10270v2.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":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/google-research/big_vision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/google-research/vision_transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","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":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/hila-chefer/robustvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/kingcong/vit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/madrylab/pretraining-distribution-shift-robustness","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/rstrudel/segmenter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/ttt496/VisionTransformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/2023-MindSpore-1/ms-code-16/tree/main/augvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/2023-MindSpore-4/Code8/tree/main/augvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/2024-MindSpore-1/Code6/tree/main/augvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/Deci-AI/super-gradients","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/vit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/MindSpore-paper-code-3/code1/tree/main/augvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/augvit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"how-to-train-your-vit-data-augmentation-and","repo_url":"https://github.com/code-implementation1/Code9/tree/main/VIT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.10270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10270"}},"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/google-research/vision_transformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/big_vision","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rstrudel/segmenter","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2024-MindSpore-1/Code6/tree/main/augvit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kingcong/vit","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/code-implementation1/Code9/tree/main/VIT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/madrylab/pretraining-distribution-shift-robustness","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-3/code1/tree/main/augvit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MS-Mind/MS-Code-02/tree/main/configs/vit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ttt496/VisionTransformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-4/Code8/tree/main/augvit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-16/tree/main/augvit","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Deci-AI/super-gradients","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hila-chefer/robustvit","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/augvit","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"4f697aeaa3747cc2","entry":"get_block_desc","repo":"google-research/big_vision","repo_kind":"official","path":"big_vision/models/bit.py","file_url":"https://github.com/google-research/big_vision/blob/HEAD/big_vision/models/bit.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4f697aeaa3747cc2"}},{"code_sha256_prefix":"37b141b05f87de19","entry":"weight_standardize","repo":"google-research/big_vision","repo_kind":"official","path":"big_vision/models/bit.py","file_url":"https://github.com/google-research/big_vision/blob/HEAD/big_vision/models/bit.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"37b141b05f87de19"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}