{"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/automix-unveiling-the-power-of-mixup","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","arxiv_id":"2103.13027","date":"2021-03-24","proceeding":null,"authors":["Zicheng Liu","Siyuan Li","Di wu","Zihan Liu","ZhiYuan Chen","Lirong Wu","Stan Z. Li"],"abstract":"Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency information to match the mixed samples and labels via complex offline optimization. However, there arises a trade-off between precise mixing policies and optimization complexity. To address this challenge, we propose a novel automatic mixup (AutoMix) framework, where the mixup policy is parameterized and serves the ultimate classification goal directly. Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i.e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework. For the generation, a learnable lightweight mixup generator, Mix Block, is designed to generate mixed samples by modeling patch-wise relationships under the direct supervision of the corresponding mixed labels. To prevent the degradation and instability of bi-level optimization, we further introduce a momentum pipeline to train AutoMix in an end-to-end manner. Extensive experiments on nine image benchmarks prove the superiority of AutoMix compared with state-of-the-art in various classification scenarios and downstream tasks.","url_abs":"https://arxiv.org/abs/2103.13027v6","url_pdf":"https://arxiv.org/pdf/2103.13027v6.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":"automix-unveiling-the-power-of-mixup","repo_url":"https://github.com/Westlake-AI/openmixup","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"automix-unveiling-the-power-of-mixup","repo_url":"https://github.com/Westlake-AI/AutoMix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"automix-unveiling-the-power-of-mixup","repo_url":"https://github.com/zeyuanyin/tiny-imagenet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"mixup","method_name":"Mixup"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ResNeXt-50 (AutoMix)","rank_in_archive_order":68,"of":265,"metrics":{"Percentage correct":"97.84"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"WRN-28-8 +AutoMix","rank_in_archive_order":67,"of":211,"metrics":{"Percentage correct":"85.16"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ResNeXt-50(32x4d) + AutoMix","rank_in_archive_order":85,"of":211,"metrics":{"Percentage correct":"83.64"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-101 (AutoMix)","rank_in_archive_order":671,"of":1060,"metrics":{"Number of params":"44.6M","Top 1 Accuracy":"80.98%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-50 (AutoMix)","rank_in_archive_order":767,"of":1060,"metrics":{"Number of params":"25.6M","Top 1 Accuracy":"79.25%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-34 (AutoMix)","rank_in_archive_order":925,"of":1060,"metrics":{"Number of params":"21.8M","Top 1 Accuracy":"76.1%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"ResNet-18 (AutoMix)","rank_in_archive_order":1001,"of":1060,"metrics":{"Number of params":"11.7M","Top 1 Accuracy":"72.05%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-places205","task":"Image Classification","dataset":"Places205","model":"AutoMix (ResNet-50 Supervised)","rank_in_archive_order":8,"of":15,"metrics":{"Top 1 Accuracy":"64.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-tiny-imagenet-1","task":"Image Classification","dataset":"Tiny ImageNet Classification","model":"ResNeXt-50 (AutoMix)","rank_in_archive_order":15,"of":23,"metrics":{"Validation Acc":"70.72%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-tiny-imagenet-1","task":"Image Classification","dataset":"Tiny ImageNet Classification","model":"ResNet18 (AutoMix)","rank_in_archive_order":20,"of":23,"metrics":{"Validation Acc":"67.33%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"ResNeXt-101 (AutoMix)","rank_in_archive_order":37,"of":60,"metrics":{"Top-1 Accuracy":"70.49%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-inaturalist-2018","task":"Image Classification","dataset":"iNaturalist 2018","model":"ResNet-50 (AutoMix)","rank_in_archive_order":49,"of":60,"metrics":{"Top-1 Accuracy":"64.73%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.13027","atlas_url":"https://app.syntology.ai/?focus=2103.13027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13027"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Westlake-AI/openmixup","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Westlake-AI/AutoMix","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zeyuanyin/tiny-imagenet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran":2,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"listed":{"samples":6,"ran":4,"repositories":2}},"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":"0d95e28fac98427f","entry":"accuracy","repo":"zeyuanyin/tiny-imagenet","repo_kind":"listed","path":"classification/utils.py","file_url":"https://github.com/zeyuanyin/tiny-imagenet/blob/HEAD/classification/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d95e28fac98427f"}},{"code_sha256_prefix":"403277d0bfbb477b","entry":"find_classes","repo":"zeyuanyin/tiny-imagenet","repo_kind":"listed","path":"classification/tiny_imagenet_dataset.py","file_url":"https://github.com/zeyuanyin/tiny-imagenet/blob/HEAD/classification/tiny_imagenet_dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"403277d0bfbb477b"}},{"code_sha256_prefix":"5ded0879a886f3c4","entry":"make_dataset","repo":"zeyuanyin/tiny-imagenet","repo_kind":"listed","path":"classification/tiny_imagenet_dataset.py","file_url":"https://github.com/zeyuanyin/tiny-imagenet/blob/HEAD/classification/tiny_imagenet_dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ded0879a886f3c4"}},{"code_sha256_prefix":"aa2ba35b3854fa14","entry":"store_model_weights","repo":"zeyuanyin/tiny-imagenet","repo_kind":"listed","path":"classification/utils.py","file_url":"https://github.com/zeyuanyin/tiny-imagenet/blob/HEAD/classification/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"none","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa2ba35b3854fa14"}},{"code_sha256_prefix":"30862aa4330bfa12","entry":"average_checkpoints","repo":"zeyuanyin/tiny-imagenet","repo_kind":"listed","path":"classification/utils.py","file_url":"https://github.com/zeyuanyin/tiny-imagenet/blob/HEAD/classification/utils.py","link_basis":"harvester_set","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":"30862aa4330bfa12"}},{"code_sha256_prefix":"30d82c52aa52dbd7","entry":"evaluate","repo":"Westlake-AI/AutoMix","repo_kind":"listed","path":"engine.py","file_url":"https://github.com/Westlake-AI/AutoMix/blob/HEAD/engine.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"30d82c52aa52dbd7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}