{"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/tokenmixup-efficient-attention-guided-token","title":"TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers","arxiv_id":"2210.07562","date":"2022-10-14","proceeding":null,"authors":["Hyeong Kyu Choi","Joonmyung Choi","Hyunwoo J. Kim"],"abstract":"Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. However, many saliency detectors require intense computation and are especially burdensome for parameter-heavy transformer models. To this end, we propose TokenMixup, an efficient attention-guided token-level data augmentation method that aims to maximize the saliency of a mixed set of tokens. TokenMixup provides x15 faster saliency-aware data augmentation compared to gradient-based methods. Moreover, we introduce a variant of TokenMixup which mixes tokens within a single instance, thereby enabling multi-scale feature augmentation. Experiments show that our methods significantly improve the baseline models' performance on CIFAR and ImageNet-1K, while being more efficient than previous methods. We also reach state-of-the-art performance on CIFAR-100 among from-scratch transformer models. Code is available at https://github.com/mlvlab/TokenMixup.","url_abs":"https://arxiv.org/abs/2210.07562v1","url_pdf":"https://arxiv.org/pdf/2210.07562v1.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":"tokenmixup-efficient-attention-guided-token","repo_url":"https://github.com/mlvlab/tokenmixup","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"CCT-7/3x1+VTM","rank_in_archive_order":71,"of":265,"metrics":{"Percentage correct":"97.78"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"CCT-7/3x1+HTM+VTM","rank_in_archive_order":86,"of":211,"metrics":{"Percentage correct":"83.57"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ViT-B/16-224+HTM","rank_in_archive_order":545,"of":1060,"metrics":{"Top 1 Accuracy":"82.37%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.07562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07562"}},"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":"deterministic:regex_extraction","url":"https://github.com/mlvlab/TokenMixup","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mlvlab/tokenmixup","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"04e9cb6d910e61ef","entry":"HorizontalTokenMixupLayer","repo":"mlvlab/tokenmixup","repo_kind":"official","path":"tokenmixup/horizontal.py","file_url":"https://github.com/mlvlab/tokenmixup/blob/HEAD/tokenmixup/horizontal.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04e9cb6d910e61ef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}