A Survey on Mixup Augmentations and Beyond
As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive labeled data are unavailable. Among existing augmentations, Mixup and relevant data-mixing methods that convexly combine s...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
08.09.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive labeled data are unavailable. Among existing augmentations, Mixup and relevant data-mixing methods that convexly combine selected samples and the corresponding labels are widely adopted because they yield high performances by generating data-dependent virtual data while easily migrating to various domains. This survey presents a comprehensive review of foundational mixup methods and their applications. We first elaborate on the training pipeline with mixup augmentations as a unified framework containing modules. A reformulated framework could contain various mixup methods and give intuitive operational procedures. Then, we systematically investigate the applications of mixup augmentations on vision downstream tasks, various data modalities, and some analysis \& theorems of mixup. Meanwhile, we conclude the current status and limitations of mixup research and point out further work for effective and efficient mixup augmentations. This survey can provide researchers with the current state of the art in mixup methods and provide some insights and guidance roles in the mixup arena. An online project with this survey is available at \url{https://github.com/Westlake-AI/Awesome-Mixup}. |
---|---|
AbstractList | As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization techniques when massive labeled data are unavailable. Among existing augmentations, Mixup and relevant data-mixing methods that convexly combine selected samples and the corresponding labels are widely adopted because they yield high performances by generating data-dependent virtual data while easily migrating to various domains. This survey presents a comprehensive review of foundational mixup methods and their applications. We first elaborate on the training pipeline with mixup augmentations as a unified framework containing modules. A reformulated framework could contain various mixup methods and give intuitive operational procedures. Then, we systematically investigate the applications of mixup augmentations on vision downstream tasks, various data modalities, and some analysis \& theorems of mixup. Meanwhile, we conclude the current status and limitations of mixup research and point out further work for effective and efficient mixup augmentations. This survey can provide researchers with the current state of the art in mixup methods and provide some insights and guidance roles in the mixup arena. An online project with this survey is available at \url{https://github.com/Westlake-AI/Awesome-Mixup}. |
Author | Chang, Yu Li, Stan Z Qin, Huafeng Liu, Zicheng Jin, Xin Zhu, Hongyu Li, Siyuan Wang, Zedong |
Author_xml | – sequence: 1 givenname: Xin surname: Jin fullname: Jin, Xin – sequence: 2 givenname: Hongyu surname: Zhu fullname: Zhu, Hongyu – sequence: 3 givenname: Siyuan surname: Li fullname: Li, Siyuan – sequence: 4 givenname: Zedong surname: Wang fullname: Wang, Zedong – sequence: 5 givenname: Zicheng surname: Liu fullname: Liu, Zicheng – sequence: 6 givenname: Yu surname: Chang fullname: Chang, Yu – sequence: 7 givenname: Huafeng surname: Qin fullname: Qin, Huafeng – sequence: 8 givenname: Stan surname: Li middlename: Z fullname: Li, Stan Z |
BookMark | eNrjYmDJy89LZWLgNDI2NtS1MDEy4mDgLS7OMjAwMDIzNzI1NeZk0HJUCC4tKkutVMjPU_DNrCgtUHAsTc9NzStJLMnMzytWSMxLUXBKrczPS-FhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXhjQwMjU3MLUwMzY-JUAQAEGjIp |
ContentType | Paper |
Copyright | 2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_31025785063 |
IEDL.DBID | BENPR |
IngestDate | Thu Oct 10 21:53:24 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_31025785063 |
OpenAccessLink | https://www.proquest.com/docview/3102578506?pq-origsite=%requestingapplication% |
PQID | 3102578506 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_3102578506 |
PublicationCentury | 2000 |
PublicationDate | 20240908 |
PublicationDateYYYYMMDD | 2024-09-08 |
PublicationDate_xml | – month: 09 year: 2024 text: 20240908 day: 08 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2024 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.569761 |
SecondaryResourceType | preprint |
Snippet | As Deep Neural Networks have achieved thrilling breakthroughs in the past decade, data augmentations have garnered increasing attention as regularization... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Artificial neural networks Data augmentation Regularization |
Title | A Survey on Mixup Augmentations and Beyond |
URI | https://www.proquest.com/docview/3102578506 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQMU-ztLAElnm6yaYWxqAtOam6iUbmlrpGqSnA2s_AJMUMfJSSr5-ZR6iJV4RpBHTArRi6rBJWJoIL6pT8ZNAYuT6wGQJKXaYGZvYFhbqgW6NAs6vQKzSYGViNDE1A07SsTq5-AUHwURYjM3Ngm9kYo6AF1x5uggysAYkFqUVCDEypecIM7OBFl8nFIgxajgrBpUVlqZUK-XkKvpkVpQUKjqXpudDdQHnFCsBevgJki4kog7Kba4izhy7MgnhoIiiORzjZWIyBBdibT5VgUEgCtjmMk40t05JTjExMDRMtTIFNLAsTQ4vENOOkxMRUSQYZfCZJ4ZeWZuAyAta64EVQFjIMLCVFpamywFqzJEmOgdnCzV0OGkBAnm-dKwA26nVd |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwY2BQMU-ztLAElnm6yaYWxqAtOam6iUbmlrpGqSnA2s_AJMUMfJSSr5-ZR6iJV4RpBHTArRi6rBJWJoIL6pT8ZNAYuT6wGQJKXaYGZvYFhbqgW6NAs6vQKzSYGVhBR25asDCwOrn6BQTBR1mMzMyBbWZjjIIWXHu4CTKwBiQWpBYJMTCl5gkzsIMXXSYXizBoOSoElxaVpVYq5Ocp-GZWlBYoOJam50J3A-UVKwB7-QqQLSaiDMpuriHOHrowC-KhiaA4HuFkYzEGFmBvPlWCQSEJ2OYwTja2TEtOMTIxNUy0MAU2sSxMDC0S04yTEhNTJRlk8JkkhV9anoHTI8TXJ97H089bmoHLCFgDgxdEWcgwsJQUlabKAmvQkiQ5aDABAFwFdjw |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Survey+on+Mixup+Augmentations+and+Beyond&rft.jtitle=arXiv.org&rft.au=Jin%2C+Xin&rft.au=Zhu%2C+Hongyu&rft.au=Li%2C+Siyuan&rft.au=Wang%2C+Zedong&rft.date=2024-09-08&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |