├── LICENSE └── README.md /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Awesome-Mix 2 | 3 | This repository contains a list of papers on the [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://arxiv.org/abs/2212.10888), and we categorize them based on our proposed taxonomy. 4 | 5 | We will try to make this list updated. If you found any error or any missed paper, please don't hesitate to open issues or pull requests. 6 | 7 | > [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://arxiv.org/abs/2212.10888) 8 | > [Chengtai Cao](https://scholar.google.com/citations?user=BbsnLQYAAAAJ&hl=en), [Fan Zhou](https://scholar.google.com/citations?user=Ihj2Rw8AAAAJ&hl=en), [Yurou Dai](https://scholar.google.com/citations?user=PdnyfV0AAAAJ&hl=en&oi=ao), and [Jianping Wang](https://scholar.google.com/citations?user=bow_liAAAAAJ&hl=en&oi=ao) 9 | > arXiv:2212.10888 10 | 11 | ## Methodology 12 | ### Mixup-based 13 | #### Mixup 14 | * [Mixup -- ICLR 2018] [Mixup: Beyond Empirical Risk Minimization](https://arxiv.org/pdf/1710.09412) [[Code](https://github.com/facebookresearch/mixup-cifar10)] 15 | * [BC Learning -- ICLR 2018] [Learning from Between-class Examples for Deep Sound Recognition](https://arxiv.org/pdf/1711.10282) [[code](https://github.com/mil-tokyo/bc_learning_sound)] 16 | * [BC Learning + -- CVRP 2018] [Between-class Learning for Image Classification](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tokozume_Between-Class_Learning_for_CVPR_2018_paper.pdf) [[code](https://github.com/mil-tokyo/bc_learning_image)] 17 | * [SamplePairing -- Arxiv 2018] [Data Augmentation by Pairing Samples for Images Classification](https://arxiv.org/pdf/1801.02929) [[_code_\*](https://github.com/junkwhinger/SamplePairing)] 18 | 19 | #### Mixng in Embedding Space 20 | * [Manifold Mixup -- ICML 2019] [Manifold Mixup: Better Representations by Interpolating Hidden States](http://proceedings.mlr.press/v97/verma19a/verma19a.pdf) [[_code_\*](https://github.com/vikasverma1077/manifold_mixup)] 21 | * [AlignMixup -- CVPR 2022] [AlignMixup: Improving Representations by Interpolating Aligned Features](https://openaccess.thecvf.com/content/CVPR2022/papers/Venkataramanan_AlignMixup_Improving_Representations_by_Interpolating_Aligned_Features_CVPR_2022_paper.pdf) [[code](https://github.com/shashankvkt/AlignMixup_CVPR22)] 22 | * [NFM -- ICLR 2022] [Noisy Feature Mixup](https://arxiv.org/pdf/2110.02180.pdf) [[code](https://github.com/erichson/noisy_mixup)] 23 | 24 | #### Adaptive Mix Strategy 25 | * [AdaMixUp -- AAAI 2019] [MixUp as Locally Linear Out-of-manifold Regularization](https://ojs.aaai.org/index.php/AAAI/article/download/4256/4134) [[_code_\*](https://github.com/SITE5039/AdaMixUp)] 26 | * [MetaMixUp -- TNNLS 2021] [MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning](https://ieeexplore.ieee.org/iel7/5962385/6104215/09366422.pdf?casa_token=yeyn9EGO8PAAAAAA:QxbqK3Y2lYbKN1eX-wOGg6rf99WUalLPE3sKzkSSuwEBmDCky3E3ozOiA5-BjYM75qmAd5EdwvA) 27 | * [AutoMix -- ECCV 2022] [AutoMix: Unveiling the Power of Mixup for Stronger Classifiers](https://arxiv.org/pdf/2103.13027) [[code](https://github.com/Westlake-AI/openmixup)] 28 | * [CAMixup -- ICLR 2021] [Combining Ensembles and Data Augmentation Can Harm Your Calibration](https://arxiv.org/pdf/2010.09875) [[code](https://github.com/google/edward2/tree/master/experimental/marginalization_mixup)] 29 | * [Nonlinear Mixup -- AAAI 2020] : [Out-of-manifold Data Augmentation for Text Classification](https://ojs.aaai.org/index.php/AAAI/article/view/5822/5678) 30 | * [AMP -- EMNLP 2021] [Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup](https://arxiv.org/pdf/2109.07177) [[code](https://github.com/PAI-SmallIsAllYourNeed/Mixup-AMP)] 31 | * [DM -- Arxiv 2022] [Decoupled Mixup for Data-efficient Learning](https://arxiv.org/pdf/2203.10761) 32 | * [Remix -- ECCV 2022] [Remix: Rebalanced Mixup ](https://arxiv.org/pdf/2007.03943) 33 | 34 | #### Sample Selection 35 | * [LADA -- EMNLP 2020] [Local Additivity based Data Augmentation for Semi-supervised NER](https://arxiv.org/pdf/2010.01677) [[code](https://github.com/GT-SALT/LADA)] 36 | * [Local Mixup -- Arxiv 2022] [Preventing Manifold Intrusion with Locality: Local Mixup](https://arxiv.org/pdf/2201.04368) [[code](https://github.com/raphael-baena/Local-Mixup)] 37 | * [Pani -- Arxiv 2019] [Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy](https://arxiv.org/pdf/1911.09307) 38 | * [HypMix -- EMNLP 2021] [HypMix: Hyperbolic Interpolative Data Augmentation](https://aclanthology.org/2021.emnlp-main.776) [[code](https://github.com/caisa-lab/hypmix-emnlp)] 39 | * [SAMix -- Arxiv 2021] [Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup](https://arxiv.org/pdf/2111.15454) 40 | * [GenLabel -- ICML 2022] [GenLabel: Mixup Relabeling using Generative Models](https://arxiv.org/pdf/2201.02354) [[code](https://github.com/UW-Madison-Lee-Lab/GenLabel_official)] 41 | * [DMix -- ACL 2022] [DMix: Adaptive Distance-aware Interpolative Mixup](https://aclanthology.org/2022.acl-short.67.pdf) [[code](https://github.com/caisa-lab/DMix-ACL)] 42 | * [M-Mix -- KDD 2022] [M-Mix: Generating Hard Negatives via Multi-sample Mixing for Contrastive Learning](https://dl.acm.org/doi/pdf/10.1145/3534678.3539248?casa_token=4rYYzEtCcxUAAAAA:JHz8mo3l1W-1bV5kh_PVrdyaIhASZkASIAMI5n-ZZM8jAyVWw-o3CXNgsi9uZIrbQLQiAbhLoV-WV8w) [[code]( https://github.com/Sherrylone/m-mix)] 43 | * [CSANMT -- ACL 2022] [Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation](https://arxiv.org/pdf/2204.06812) [[code](https://github.com/pemywei/csanmt)] 44 | * [RegMixup -- NIPS 2022] [RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness](https://arxiv.org/pdf/2206.14502) [[code](https://github.com/FrancescoPinto/RegMixup)] 45 | 46 | #### Saliency \& Style For Guidance 47 | * [SuperMix -- CVPR 2021] [SuperMix: Supervising the Mixing Data Augmentation](http://openaccess.thecvf.com/content/CVPR2021/papers/Dabouei_SuperMix_Supervising_the_Mixing_Data_Augmentation_CVPR_2021_paper.pdf) [[code](https://github.com/alldbi/SuperMix)] 48 | * [Superpixel-Mix -- BMVC 2021] [Robust Semantic Segmentation with Superpixel-Mix](https://arxiv.org/pdf/2108.00968) 49 | * [StyleMix -- CVPR 2021] [StyleMix: Separating Content and Style for Enhanced Data Augmentation](https://openaccess.thecvf.com/content/CVPR2021/papers/Hong_StyleMix_Separating_Content_and_Style_for_Enhanced_Data_Augmentation_CVPR_2021_paper.pdf) [[code](https://github.com/alsdml/StyleMix)] 50 | * [Mixstyle -- ICLR 2021] : [Domain Generalization with Mixstyle](https://arxiv.org/pdf/2104.02008) [[code](https://github.com/KaiyangZhou/mixstyle-release)] 51 | * [MoEx -- CVPR 2021] [On Feature Normalization and Data Augmentation](http://openaccess.thecvf.com/content/CVPR2021/papers/Li_On_Feature_Normalization_and_Data_Augmentation_CVPR_2021_paper.pdf) [[code](https://github.com/Boyiliee/MoEx)] 52 | * [Mixup-with-AUM-and-SM -- ACL 2022] [On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency](https://arxiv.org/pdf/2203.07559) [[code](https://github.com/seoyeon-p/MixUp-Guided-by-AUM-and-Saliency-Map)] 53 | * [XAI Mixup -- TKDD 2022] [Explainability-based Mixup Approach for Text Data Augmentation](https://dl.acm.org/doi/pdf/10.1145/3533048) 54 | * [TokenMixup -- Arxiv 2022] [TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers](https://arxiv.org/pdf/2210.07562.pdf) [[code](https://github.com/mlvlab/TokenMixup)] 55 | * [SciMix -- Arxiv 2022] [Swapping Semantic Contents for Mixing Images](https://arxiv.org/pdf/2205.10158.pdf) 56 | 57 | #### Diversity in Mixup 58 | * [BatchMixup -- IJCNLP 2021] [BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch](https://aclanthology.org/2021.findings-acl.434.pdf) 59 | * [K-Mixup -- Arxiv 2021] [K-Mixup Regularization for Deep Learning via Optimal Transport](https://arxiv.org/pdf/2106.02933) 60 | * [MultiMix -- Arxiv 2022] [Teach Me How to Interpolate a Myriad of Embeddings](https://arxiv.org/pdf/2205.14230) 61 | * [MixMo -- CVPR 2021] [MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks](https://openaccess.thecvf.com/content/ICCV2021/papers/Rame_MixMo_Mixing_Multiple_Inputs_for_Multiple_Outputs_via_Deep_Subnetworks_ICCV_2021_paper.pdf) [[code](https://github.com/alexrame/mixmo-pytorch)] 62 | * [DMixup \& DCutmix -- Arxiv 2021] [Observations on K-image Expansion of Image-mixing Augmentation for Classification](https://arxiv.org/pdf/2110.04248) 63 | * [PixMix -- CVPR 2022] [PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures](https://openaccess.thecvf.com/content/CVPR2022/papers/Hendrycks_PixMix_Dreamlike_Pictures_Comprehensively_Improve_Safety_Measures_CVPR_2022_paper.pdf) [[code](https://github.com/andyzoujm/pixmix)] 64 | 65 | #### Miscellaneous Mixup Methods 66 | * [GIF -- Arxiv 2021] [Guided Interpolation for Adversarial Training](https://arxiv.org/pdf/2102.07327) 67 | * [MWh -- ICIG 2021] [Mixup Without Hesitation](https://arxiv.org/pdf/2101.04342) [[code](https://github.com/yuhao318/mwh)] 68 | * [AutoMix -- ECCV 2020] [AutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter Learning](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123550630.pdf) [[_code_\*](https://github.com/ReBoRn8888/AutoMix)] 69 | * [RegMix -- Arxiv 2021] [RegMix: Data Mixing Augmentation for Regression](https://arxiv.org/pdf/2106.03374.pdf) 70 | 71 | ### Cutmix-based 72 | #### Cutmix 73 | * [Cutmix -- ICCV 2019] [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://openaccess.thecvf.com/content_ICCV_2019/papers/Yun_CutMix_Regularization_Strategy_to_Train_Strong_Classifiers_With_Localizable_Features_ICCV_2019_paper.pdf) [[Code](https://github.com/clovaai/CutMix-PyTorch)] 74 | * [MixdedExample -- WACV 2019] [Improved Mixed-example Data Augmentation](https://ieeexplore.ieee.org/iel7/8642793/8658235/08659168.pdf?casa_token=vxPrsAdypIAAAAAA:3D8UWPSlFNhIpF7K9KKb3hSdDF79p3DXchPTv5qRBQHlJ8VwyDbldMUp0rtbxGVR5dDwBHMwfM8) [[code](https://github.com/ceciliaresearch/MixedExample)] 75 | * [RICAP -- ACML 2018] [RICAP: Random Image Cropping and Patching Data Augmentation for Deep CNNs](http://proceedings.mlr.press/v95/takahashi18a/takahashi18a.pdf) [[_code_\*](https://github.com/4uiiurz1/pytorch-ricap)] 76 | 77 | #### Integration with Saliency Information 78 | * [Attentive Cutmix -- ICASSP 2020] [Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning based Image Classification](https://arxiv.org/pdf/2003.13048) [[_code_\*](https://github.com/xden2331/attentive_cutmix)] 79 | * [FocusMix -- ICTC 2020] [Where to Cut and Paste: Data Regularization with Selective Features](https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9289404&casa_token=ZOkscThNTpQAAAAA:AhalGFG_kjrXgaEZRzo5E3QN2mNC7gdnF1PtAd7MG0-rXbaHSS1JzZiM5wWv7hLR8plKxXy4F3U) 80 | * [TransMix -- CVPR 2022] [TransMix: Attend to Mix for Vision Transformers](https://openaccess.thecvf.com/content/CVPR2022/papers/Chen_TransMix_Attend_To_Mix_for_Vision_Transformers_CVPR_2022_paper.pdf) [[code](https://github.com/Beckschen/TransMix)] 81 | * [TL-Align -- Arxiv 2021] [Token-Label Alignment for Vision Transformers](https://arxiv.org/pdf/2210.06455) [[code](https://github.com/Euphoria16/TL-Align)] 82 | * [SaliencyMix -- ILCR 2021] [SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization](https://arxiv.org/pdf/2006.01791) [[code](https://github.com/SaliencyMix/SaliencyMix)] 83 | * [Puzzle Mix -- ICML 2020] [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](http://proceedings.mlr.press/v119/kim20b/kim20b.pdf) [[code](https://github.com/snu-mllab/PuzzleMix)] 84 | * [SSMix -- ACL 2021] [SSMix: Saliency-based Span Mixup for Text Classification](https://arxiv.org/pdf/2106.08062) [[code](https://github.com/clovaai/ssmix)] 85 | * [SnapMix -- AAAI 2021] [SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data](https://ojs.aaai.org/index.php/AAAI/article/view/16255/16062) [[code](https://github.com/Shaoli-Huang/SnapMix)] 86 | * [Attribute Mix -- VCIP 2020] [Attribute Mix: Semantic Data Augmentation for Fine Grained Recognition](https://arxiv.org/pdf/2004.02684) 87 | * [ResizeMix -- Arxiv 2020] [ResizeMix: Mixing Data with Preserved Object Information and True Labels](https://arxiv.org/pdf/2012.11101.pdf) [[_code_\*](https://github.com/HarborYuan/pytorch-macos-bench)] 88 | 89 | #### Improved Divergence 90 | * [Saliency Grafting -- AAAI 2022] [Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing](https://ojs.aaai.org/index.php/AAAI/article/view/20766/20525) 91 | * [Co-Mixup -- ICLR 2021] [Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity](https://arxiv.org/pdf/2102.03065) [[code](https://github.com/snu-mllab/Co-Mixup)] 92 | * [RecursiveMix -- Arxiv 2022] [RecursiveMix: Mixed Learning with History](https://arxiv.org/pdf/2203.06844) [[code](https://github.com/megvii-research/RecursiveMix)] 93 | 94 | #### Border Smooth 95 | * [SmoothMix -- CVPR 2020] [SmoothMix: A Simple Yet Effective Data Augmentation to Train Robust Classifiers](https://openaccess.thecvf.com/content_CVPRW_2020/papers/w45/Lee_SmoothMix_A_Simple_Yet_Effective_Data_Augmentation_to_Train_Robust_CVPRW_2020_paper.pdf) [[code](https://github.com/jh-jeong/smoothmix)] 96 | * [HMix \& GMix -- Arxiv 2022] [A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective](https://arxiv.org/pdf/2208.09913) [[code](https://github.com/naver-ai/hmix-gmix)] 97 | 98 | #### Other Cutmix Techniques 99 | * [PatchUp -- AAAI 2022] [PatchUp: A Regularization Technique for Convolutional Neural Networks](https://arxiv.org/pdf/2006.07794) [[code](https://github.com/chandar-lab/PatchUp)] 100 | * [TokenMix -- ECCV 2022] [TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers](https://arxiv.org/pdf/2207.08409) [[code](https://github.com/Sense-X/TokenMix)] 101 | * [ScoreMix -- CVPR 2022] [ScoreNet: Learning Non-uniform Attention and Augmentation for Transformer-based Histopathological Image Classification](https://arxiv.org/pdf/2202.07570) 102 | * [GridMix -- Pattern Recognition 2021] [GridMix: Strong Regularization through Local Context Mapping](https://www.sciencedirect.com/science/article/pii/S0031320320303976?casa_token=oQ7NhHPxs1cAAAAA:U0cFG2ASbufAHEPW4m14bxaUMsXK3QE6ke-sjpvbpkcbbLAd_YFSUEbUU2DECq3H7IjtW2dRpAQ) 103 | * [PatchMix -- BMWC 2021] [Evolving Image Compositions for Feature Representation Learning](https://arxiv.org/pdf/2106.09011) 104 | * [ChessMix -- SIBGRAPI 2021] [ChessMix: Spatial Context Data Augmentation for Remote Sensing Semantic Segmentation](https://ieeexplore.ieee.org/iel7/9643073/9642965/09643145.pdf) [[code](https://github.com/matheusbarrosp/chessmix)] 105 | * [ICC -- ICPS 2021] [Intra-class Cutmix for Unbalanced Data Augmentation](https://dl.acm.org/doi/pdf/10.1145/3457682.3457719) 106 | 107 | ### Beyond Mixup \& Cutmix 108 | #### Mixing with itself 109 | * [DJMix -- Arxiv 2021] [DJMix: Unsupervised Task-agnostic Augmentation for Improving Robustness](https://openreview.net/pdf?id=0n3BaVlNsHI) 110 | * [CutBlur -- CVPR 2020] [Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy](http://openaccess.thecvf.com/content_CVPR_2020/papers/Yoo_Rethinking_Data_Augmentation_for_Image_Super-resolution_A_Comprehensive_Analysis_and_CVPR_2020_paper.pdf) [[code](https://github.com/clovaai/cutblur)] 111 | #### Incorporating multiple MixDA approaches 112 | * [RandomMix -- Arxiv 2022 ] [RandomMix: A Mixed Sample Data Augmentation Method with Multiple Mixed Modes](https://arxiv.org/pdf/2205.08728) 113 | * [AugRmixAT -- ICME 2002] [AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance](https://arxiv.org/abs/2207.10290) 114 | #### Integrating with other DA methods 115 | * [SuperpixelGridMix -- Arxiv 2022] [SuperpixelGridCut, SuperpixelGridMean and SuperpixelGridMix Data Augmentation](https://arxiv.org/pdf/2204.08458) [[code](https://github.com/hammoudiproject/SuperpixelGridMasks)] 116 | * [AugMix -- ICLR 2020] [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://openreview.net/pdf?id=S1gmrxHFvB) [[code](https://github.com/google-research/augmix)] 117 | * [StackMix -- UAI 2021] [StackMix: A Complementary Mix Algorithm](https://proceedings.mlr.press/v180/chen22b/chen22b.pdf) 118 | * [ClassMix -- WACV 2021] [ClassMix: Segmentation-based Data Augmentation for Semi-supervised Learning](https://arxiv.org/pdf/2007.07936.pdf) [[code](https://github.com/WilhelmT/ClassMix)] 119 | * [CropMix -- Arxiv 2022] [CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping](https://arxiv.org/pdf/2205.15955.pdf) [[code](https://github.com/JunlinHan/CropMix)] 120 | 121 | 122 | ## MixDA Applications 123 | ### Semi-Supervised Learning 124 | * [ICT -- IJCAI 2019] [Interpolation Consistency Training for Semi-Supervised Learning](https://arxiv.org/pdf/1903.03825.pdf?ref=https://githubhelp.com) [[code](https://github.com/vikasverma1077/ICT)] 125 | * [MixMatch -- NIPS 2019] [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://proceedings.neurips.cc/paper/2019/file/1cd138d0499a68f4bb72bee04bbec2d7-Paper.pdf) [[code](https://github.com/google-research/mixmatch)] 126 | * [ReMixMatch -- Arxiv 2019] [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://arxiv.org/pdf/1911.09785.pdf) [[code](https://github.com/google-research/remixmatch)] 127 | * [DivideMix -- ICLR 2020] [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://arxiv.org/pdf/2002.07394.pdf) [[code](https://github.com/LiJunnan1992/DivideMix)] 128 | * [CowMix/CowOut -- Arxiv 2020] [Milking CowMask for Semi-Supervised Image Classification](https://arxiv.org/pdf/2003.12022.pdf) [[code](https://github.com/google-research/google-research/tree/master/milking_cowmask)] 129 | * [MixPUL -- Arxiv 2020] [MixPUL: Consistency-based Augmentation for Positive and Unlabeled Learning](https://arxiv.org/pdf/2004.09388.pdf) [[code](https://github.com/Stomach-ache/MixPUL)] 130 | * [P3Mix -- ICLR 2022] [Who is Your Right Mixup Partner in Positive and Unlabeled Learning](https://openreview.net/pdf?id=NH29920YEmj) 131 | 132 | ### Contrastive Learning 133 | * [MixCo -- Arxiv 2022] [MixCo: Mix-up Contrastive Learning for Visual Representation](https://arxiv.org/pdf/2010.06300) [[cdoe](https://github.com/Lee-Gihun/MixCo-Mixup-Contrast)] 134 | * [Core-tuning -- NIPS 2021] [Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-regularized Fine-tuning](https://proceedings.neurips.cc/paper/2021/file/fa14d4fe2f19414de3ebd9f63d5c0169-Paper.pdf) [[code](https://github.com/Vanint/Core-tuning)] 135 | * [Feature Transformation -- ICCV 2021] [Improving Contrastive Learning by Visualizing Feature Transformation](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhu_Improving_Contrastive_Learning_by_Visualizing_Feature_Transformation_ICCV_2021_paper.pdf) [[code](https://github.com/DTennant/CL-Visualizing-Feature-Transformation)] 136 | * [Mochi -- NIPS 2020] [Hard Negative Mixing for Contrastive Learning](https://proceedings.neurips.cc/paper/2020/file/f7cade80b7cc92b991cf4d2806d6bd78-Paper.pdf) [[code](https://europe.naverlabs.com/mochi)] 137 | * [Comix -- NIPS 2021] [Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing](https://proceedings.neurips.cc/paper/2021/file/c47e93742387750baba2e238558fa12d-Paper.pdf) [[code](https://cvir.github.io/projects/comix)] 138 | * [MixSiam -- Arxiv 2021] [MixSiam: A Mixture-based Approach to Self-Supervised Representation Learning](https://arxiv.org/pdf/2111.02679) 139 | * [Un-Mix -- AAAI 2022] [Un-mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning](https://ojs.aaai.org/index.php/AAAI/article/view/20119/19878) [[code](https://github.com/szq0214/Un-Mix)] 140 | * [ScaleMix -- CVPR 2022] [On the Importance of Asymmetry for Siamese Representation Learning](https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_On_the_Importance_of_Asymmetry_for_Siamese_Representation_Learning_CVPR_2022_paper.pdf) [[code](https://github.com/facebookresearch/asym-siam)] 141 | * [BSIM -- Arxiv 2020] [Beyond Single Instance Multi-view Unsupervised Representation Learning](https://arxiv.org/pdf/2011.13356) 142 | * [i-Mix -- ICLR 2021] [i-mix: A Domain-agnostic Strategy for Contrastive Representation Learning](https://arxiv.org/pdf/2010.08887) [[code](https://github.com/kibok90/imix)] 143 | * [MCL -- PRL 2022] [Mixing up Contrastive Learning: Self-Supervised Representation Learning for Time Series](https://www.sciencedirect.com/science/article/pii/S0167865522000502) [[code](https://github.com/Wickstrom/MixupContrastiveLearning)] 144 | * [CLIM -- BMWC 2020] [Center-wise Local Image Mixture For Contrastive Representation Learning](https://arxiv.org/pdf/2011.02697) 145 | * [SDMP -- CVPR 2022] [A Simple Data Mixing Prior for Improving Self-Supervised Learning](https://openaccess.thecvf.com/content/CVPR2022/papers/Ren_A_Simple_Data_Mixing_Prior_for_Improving_Self-Supervised_Learning_CVPR_2022_paper.pdf) [[code](https://github.com/OliverRensu/SDMP)] 146 | * [Similarity Mixup -- CVPR 2022] [Recall@k Surrogate Loss with Large Batches and Similarity Mixup](https://openaccess.thecvf.com/content/CVPR2022/papers/Patel_Recallk_Surrogate_Loss_With_Large_Batches_and_Similarity_Mixup_CVPR_2022_paper.pdf) [[code](https://github.com/yash0307/RecallatK)] 147 | * [ProGC-Mix -- ICML] [ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning](https://proceedings.mlr.press/v162/xia22b/xia22b.pdf) [[code](https://github.com/junxia97/ProGCL)] 148 | 149 | ### Metric Learning 150 | 1. [Embedding Expansion -- CVPR 2020] [Embedding Expansion: Augmentation in Embedding Space for Deep Metric Learning](http://openaccess.thecvf.com/content_CVPR_2020/papers/Ko_Embedding_Expansion_Augmentation_in_Embedding_Space_for_Deep_Metric_Learning_CVPR_2020_paper.pdf)(2020) [[code](https://github.com/clovaai/embedding-expansion)] 151 | 2. [Metrix -- ICLR 2022] [It Takes Two to Tango: Mixup for Deep Metric Learning](https://arxiv.org/pdf/2106.04990.pdf)(2022) [[code](https://tinyurl.com/metrix-iclr)] 152 | 153 | ### Adversarial Training 154 | * [IAT -- AISec 2019] [Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy](https://dl.acm.org/doi/pdf/10.1145/3338501.3357369) 155 | * [AVmixup -- CVPR 2020] [Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization](https://openaccess.thecvf.com/content_CVPR_2020/papers/Lee_Adversarial_Vertex_Mixup_Toward_Better_Adversarially_Robust_Generalization_CVPR_2020_paper.pdf) [[code](https://github.com/xuyinhu/AVmixup)] 156 | * [AMDA ACL/IJNCLP 2021] [Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning](https://aclanthology.org/2021.findings-acl.137.pdf) [[code](https://github.com/thunlp/MixADA)] 157 | * [M-TLAT -- ECCV 2020] [Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training](https://arxiv.org/pdf/2008.08384) 158 | * [AOM -- Arxiv 2021] [Adversarially Optimized Mixup for Robust Classification](https://arxiv.org/pdf/2103.11589) 159 | * [MixACM -- NIPS 2021] : [MixACM: Mixup-based Robustness Transfer via Distillation of Activated Channel Maps](https://proceedings.neurips.cc/paper/2021/file/240c945bb72980130446fc2b40fbb8e0-Paper.pdf) [[code](https://awaisrauf.github.io/MixACM)] 160 | * [Mixup-SSAT -- Arxiv 2022] [Semi-Supervised Semantics-guided Adversarial Training for Trajectory Prediction](https://arxiv.org/pdf/2205.14230) 161 | * [MI -- ICLR 2020] [Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks](https://arxiv.org/pdf/1909.11515) [[code](https://github.com/P2333/Mixup-Inference)] 162 | 163 | ### Generative Models 164 | * [Shot VAE -- AAAI 2021][SHOT-VAE: Semi-Supervised Deep Generative Models with Label-aware ELBO Approximations](https://ojs.aaai.org/index.php/AAAI/article/view/16909/16716) [[code](https://github.com/FengHZ/SHOT-VAE)] 165 | * [AAE -- ICPR 2018] [Data Augmentation via Latent Space Interpolation for Image Classification](https://ieeexplore.ieee.org/iel7/8527858/8545020/08545506.pdf?casa_token=pjiWDeNyO-UAAAAA:xzH6WaFN4ik6otSGYZQ4rYsgtGVtyPK9wTyBgT12Ubrfravtdj3mYY-eIHqcXvKWuyi9JQ_Rx14) 166 | * [VarMixup -- Arxiv 2020] [VarMixup: Exploiting the Latent Space for Robust Training and Inference](https://arxiv.org/pdf/2003.06566v1.pdf) 167 | * [ACAI -- ICLR 2019] [Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer](https://arxiv.org/pdf/1807.07543.pdf) [[code](https://github.com/brain-research/acai)] 168 | * [AMR -- NIPS 2019] [On Adversarial Mixup Resynthesis](https://proceedings.neurips.cc/paper/2019/file/f708f064faaf32a43e4d3c784e6af9ea-Paper.pdf) [[code](https://github.com/christopher-beckham/amr)] 169 | 170 | ### Domain Adaption 171 | * [VMT -- Arxiv 2019] [Virtual Mixup Training for Unsupervised Domain Adaptation](https://arxiv.org/pdf/1905.04215.pdf) [[code](https://github.com/xudonmao/VMT)] 172 | * [IIMT -- Arxiv 2020] [Improve Unsupervised Domain Adaptation with Mixup Training](https://arxiv.org/pdf/2001.00677) 173 | * [DM-ADA -- AAAI 2020] [Adversarial Domain Adaptation with Domain Mixup](https://ojs.aaai.org/index.php/AAAI/article/view/6123/5979) 174 | * [DMRL -- ECCV 2020] [Dual Mixup Regularized Learning for Adversarial Domain Adaptation](https://arxiv.org/pdf/2007.03141) [[code](https://github.com/YuanWu3/Dual-Mixup-Regularized-Learning-for-Adversarial-Domain-Adaptation)] 175 | * [SLM -- NIPS 2021] [Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation](https://arxiv.org/pdf/2012.03358) [[code](https://github.com/CVIR/Select-Label-Mix-SLM-PDA)] 176 | 177 | ### Natural Language Processing 178 | * [WordMixup & SenMixup -- Arxiv 2019] [Augmenting Data with Mixup for Sentence Classification: An Empirical Study](https://arxiv.org/pdf/1905.08941.pdf) 179 | * [Mixup-Transformer -- COLING 2020] [Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks](https://arxiv.org/pdf/2010.02394) 180 | * [Calibrated-BERT-Fine-Tuning -- EMNLP 2020] [Calibrated Language Model Fine-tuning for In- and Out-of-distribution Data](https://arxiv.org/pdf/2010.11506) [[code](https://github.com/Lingkai-Kong/Calibrated-BERT-Fine-Tuning)] 181 | * [Emix -- COLING 2020] [Augmenting NLP Models using Latent Feature Interpolations](https://aclanthology.org/2020.coling-main.611) 182 | * [TreeMix -- NAALC 2022] [TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding](https://arxiv.org/pdf/2205.06153) 183 | * [MixText -- ACL 2020] [MixText: Linguistically-informed Interpolation of Hidden Space for Semi-Supervised Text Classification](https://arxiv.org/pdf/2004.12239.pdf) [[code](https://github.com/GT-SALT/MixText)] 184 | * [SeqMix -- EMNLP 2020] [Sequence-level Mixed Sample Data Augmentation](https://arxiv.org/pdf/2011.09039) [[code](https://github.com/dguo98/seqmix)] 185 | * [SeqMix -- EMNLP 2020] [Seqmix: Augmenting Active Sequence Labeling via Sequence Mixup](https://arxiv.org/pdf/2010.02322) [[code](https://github.com/rz-zhang/SeqMix)] 186 | * [AdvAug -- ACL 2020] [AdvAug: Robust Adversarial Augmentation for Neural Machine Translation](https://arxiv.org/pdf/2006.11834) 187 | * [STEMM -- ACL 2022] [STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation](https://arxiv.org/pdf/2203.10426) [[code](https://github.com/ictnlp/STEMM)] 188 | * [MixDiversity -- EMNLP 2021] [Mixup Decoding for Diverse Machine Translation](https://arxiv.org/pdf/2109.03402) 189 | * [XMixup -- ICLR 2022] [Enhancing Cross-lingual Transfer by Manifold Mixup](https://arxiv.org/pdf/2205.04182) [[code](https://github.com/yhy1117/X-Mixup)] 190 | * [mXEncDec -- ACL 2022] [Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation](https://arxiv.org/pdf/2203.07627) 191 | 192 | ### Graph Neural Networks 193 | * [GraphMix -- AAAI 2021] [GraphMix: Improved Training of GNNs for Semi-Supervised Learning](https://ojs.aaai.org/index.php/AAAI/article/view/17203/17010) [[code](https://github.com/vikasverma1077/GraphMix)] 194 | * [PMRGNN -- Symmetry 2022] [Graph Mixed Random Network based on PageRank](https://www.mdpi.com/2073-8994/14/8/1678/pdf) 195 | * [NodeAug -- CDS 2021] [Node Augmentation Methods for Graph Neural Network based Object Classification](https://ieeexplore.ieee.org/iel7/9463177/9463158/09463199.pdf?casa_token=xtakWOywRx4AAAAA:6kQ4iVsW6_zOpR5MDrlBUjGIpBo-DQfI13uQxd4iL9zcDlJwAYB8gpjraia2nS9pewl78ygL4kg) 196 | * [MixGNN -- WWW 2021] [Mixup for Node and Graph Classification](https://dl.acm.org/doi/pdf/10.1145/3442381.3449796) 197 | * [GraphMixup -- Arxiv 2022] [GraphMixup: Improving Class-imbalanced Node Classification on Graphs by Self-Supervised Context Prediction](https://arxiv.org/pdf/2106.11133.pdf) 198 | * [G-Mixup -- ICML 2022] [G-Mixup: Graph Data Augmentation for Graph Classification](https://arxiv.org/pdf/2202.07179) 199 | * [Graph Transplant -- MiniCon 2022] [Graph Transplant: Node Saliency-guided Graph Mixup with Local Structure Preservation](https://www.aaai.org/AAAI22Papers/AAAI-11745.ParkJ.pdf) 200 | * [GraphSMOTE -- Arxiv 2022] [Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks](https://arxiv.org/pdf/2206.05335.pdf) [[code](https://github.com/TianxiangZhao/GraphSmote)] 201 | 202 | ### Federated Learning 203 | * [Mix2FLD -- CL 2020] [Mix2FLD: Downlink Federated Learning after Uplink Federated Distillation with Two-way Mixup](https://ieeexplore.ieee.org/iel7/4234/5534602/09121290.pdf) 204 | * [XORMixup -- Arxiv 2020] [XOR Mixup: Privacy-preserving Data Augmentation for One-shot Federated Learning](https://arxiv.org/pdf/2006.05148) 205 | * [FedMix --ICLR 2021] [FedMix: Approximation of Mixup under Mean Augmented Federated Learning](http://arxiv.org/pdf/2107.00233) [[code](https://github.com/smduan)] 206 | 207 | ### Other Applications 208 | #### Point Clound 209 | * [PointMix -- ECCV 2020] [PointMixup: Augmentation for Point Clouds](https://arxiv.org/pdf/2008.06374) [[code](https://github.com/yunlu-chen/PointMixup)] 210 | * [PA-AUG -- IROS 2021] [Part-aware Data Augmentation for 3D Object Detection in Point Cloud](https://ieeexplore.ieee.org/iel7/9635848/9635849/09635887.pdf?casa_token=0mFjLnp6YCYAAAAA:xolNh7Ecmuzu3t0vc_QaEcBIcFQYEIMiDScD7zTNWu0rPwhzIbnNQTbydAtW64WUfJxeoh4qt_w) [[code](https://github.com/sky77764/pa-aug.pytorch)] 211 | * [RSMix -- CVPR 2021] [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://openaccess.thecvf.com/content/CVPR2021/papers/Lee_Regularization_Strategy_for_Point_Cloud_via_Rigidly_Mixed_Sample_CVPR_2021_paper.pdf) [[code](https://github.com/dogyoonlee/RSMix)] 212 | #### Multiple-modal Learning 213 | * [CMC -- ICML 2022] [VLMixer: Unpaired Vision-language Pre-training via Cross-Modal CutMix](https://proceedings.mlr.press/v162/wang22h/wang22h.pdf) [[code](https://github.com/ttengwang/VLMixer)] 214 | 215 | 216 | ## Explainability Analysis of MixDA 217 | ### Vicinal Risk Minimization 218 | * [VRM -- NeurIPS 2000] [Vicinal Risk Minimization](https://proceedings.neurips.cc/paper/2000/file/ba9a56ce0a9bfa26e8ed9e10b2cc8f46-Paper.pdf) 219 | 220 | ### Model Regularization 221 | * [Regularization -- Arxiv 2020] [On Mixup Regularization](http://arxiv.org/pdf/2006.06049) 222 | * [Regularization -- IEEE Access 2018] [Understanding Mixup Training Methods](https://ieeexplore.ieee.org/iel7/6287639/8274985/08478159.pdf) [[code](https://github.com/liangdaojun/spatial-mixup)] 223 | * [Regularization -- ICLR 2021] [How does Mixup Help with Robustness and Generalization?](http://arxiv.org/pdf/2010.04819) 224 | * [Regularization -- Arxiv 2022] [A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective](http://arxiv.org/pdf/2208.09913) [[code](https://github.com/naver-ai/hmix-gmix)] 225 | 226 | ### Uncertainty \& Calibration 227 | * [Uncertainty \& Calibration -- ICML 2022] [When and How Mixup Improves Calibration](https://proceedings.mlr.press/v162/zhang22f/zhang22f.pdf) 228 | * [Uncertainty \& Calibration -- NIPS 2019] [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://proceedings.neurips.cc/paper/2019/file/36ad8b5f42db492827016448975cc22d-Paper.pdf) 229 | 230 | ## License 231 | This project is released under the [Apache 2.0 license](LICENSE). 232 | 233 | ## Related Project 234 | * [Awesome-Mixup](https://github.com/Westlake-AI/Awesome-Mixup) 235 | * [OpenMixup](https://github.com/Westlake-AI/openmixup) 236 | * [Awesome-Mixup](https://github.com/lionel-hing/Awesome-Mixup) 237 | * [awesome-mixup](https://github.com/demoleiwang/awesome-mixup) 238 | --------------------------------------------------------------------------------