A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective

21 August 2022

ArXiv (abs)PDF HTML Github (21★)

Papers citing "A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective"

50 / 61 papers shown

Title
SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe Yuxin Xiao Shujian Zhang Wenxuan Zhou Marzyeh Ghassemi Sanqiang Zhao 390 0 0 07 Oct 2024
For Better or For Worse? Learning Minimum Variance Features With Label Augmentation Muthuraman Chidambaram Rong Ge AAML 83 0 0 10 Feb 2024
A Simple Data Mixing Prior for Improving Self-Supervised Learning Sucheng Ren Huiyu Wang Zhengqi Gao Shengfeng He Alan Yuille Yuyin Zhou Cihang Xie 47 35 0 15 Jun 2022
GenLabel: Mixup Relabeling using Generative Models Jy-yong Sohn Liang Shang Hongxu Chen Jaekyun Moon Dimitris Papailiopoulos Kangwook Lee VLM 74 15 0 07 Jan 2022
Data Augmentation Can Improve Robustness Sylvestre-Alvise Rebuffi Sven Gowal D. A. Calian Florian Stimberg Olivia Wiles Timothy A. Mann AAML 60 286 0 09 Nov 2021
Towards Understanding the Data Dependency of Mixup-style Training Muthuraman Chidambaram Xiang Wang Yuzheng Hu Chenwei Wu Rong Ge UQCV 75 24 0 14 Oct 2021
Observations on K-image Expansion of Image-Mixing Augmentation for Classification Joonhyun Jeong Sungmin Cha Jongwon Choi Sangdoo Yun Taesup Moon Y. Yoo VLM 67 7 0 08 Oct 2021
ResNet strikes back: An improved training procedure in timm Ross Wightman Hugo Touvron Hervé Jégou AI4TS 258 497 0 01 Oct 2021
StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures Sanghyuk Chun Song Park 41 6 0 24 Aug 2021
SpecMix : A Mixed Sample Data Augmentation method for Training withTime-Frequency Domain Features Gwantae Kim D. Han Hanseok Ko 88 45 0 06 Aug 2021
k-Mixup Regularization for Deep Learning via Optimal Transport Kristjan Greenewald Anming Gu Mikhail Yurochkin Justin Solomon Edward Chien 74 19 0 05 Jun 2021
On Linear Stability of SGD and Input-Smoothness of Neural Networks Chao Ma Lexing Ying MLT 39 44 0 27 May 2021
MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition Linghui Meng Jin Xu Xu Tan Jindong Wang Tao Qin Bo Xu VLM 101 78 0 25 Feb 2021
SWAD: Domain Generalization by Seeking Flat Minima Junbum Cha Sanghyuk Chun Kyungjae Lee Han-Cheol Cho Seunghyun Park Yunsung Lee Sungrae Park MoMe 283 454 0 17 Feb 2021
When and How Mixup Improves Calibration Linjun Zhang Zhun Deng Kenji Kawaguchi James Zou UQCV 49 68 0 11 Feb 2021
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision Chao Jia Yinfei Yang Ye Xia Yi-Ting Chen Zarana Parekh Hieu H. Pham Quoc V. Le Yun-hsuan Sung Zhen Li Tom Duerig VLM CLIP 445 3,856 0 11 Feb 2021
Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity Jang-Hyun Kim Wonho Choo Hosan Jeong Hyun Oh Song 252 180 0 05 Feb 2021
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels Sangdoo Yun Seong Joon Oh Byeongho Heo Dongyoon Han Junsuk Choe Sanghyuk Chun 482 146 0 13 Jan 2021
Training data-efficient image transformers & distillation through attention Hugo Touvron Matthieu Cord Matthijs Douze Francisco Massa Alexandre Sablayrolles Hervé Jégou ViT 387 6,768 0 23 Dec 2020
ResizeMix: Mixing Data with Preserved Object Information and True Labels Jie Qin Jiemin Fang Qian Zhang Wenyu Liu Xingang Wang Xinggang Wang 72 86 0 21 Dec 2020
VideoMix: Rethinking Data Augmentation for Video Classification Sangdoo Yun Seong Joon Oh Byeongho Heo Dongyoon Han Jinhyung Kim 415 74 0 07 Dec 2020
MixCo: Mix-up Contrastive Learning for Visual Representation Sungnyun Kim Gihun Lee Sangmin Bae Seyoung Yun SSL 147 80 0 13 Oct 2020
How Does Mixup Help With Robustness and Generalization? Linjun Zhang Zhun Deng Kenji Kawaguchi Amirata Ghorbani James Zou AAML 84 251 0 09 Oct 2020
Sharpness-Aware Minimization for Efficiently Improving Generalization Pierre Foret Ariel Kleiner H. Mobahi Behnam Neyshabur AAML 192 1,350 0 03 Oct 2020
Hard Negative Mixing for Contrastive Learning Yannis Kalantidis Mert Bulent Sariyildiz Noé Pion Philippe Weinzaepfel Diane Larlus SSL 134 643 0 02 Oct 2020
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup Jang-Hyun Kim Wonho Choo Hyun Oh Song AAML 89 390 0 15 Sep 2020
Input Hessian Regularization of Neural Networks Waleed Mustafa Robert A. Vandermeulen Marius Kloft AAML 46 12 0 14 Sep 2020
Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization Yu-Ting Chang Qiaosong Wang Wei-Chih Hung Robinson Piramuthu Yi-Hsuan Tsai Ming-Hsuan Yang UQCV WSOL 68 34 0 03 Aug 2020
Improving Generalization in Meta-learning via Task Augmentation Huaxiu Yao Long-Kai Huang Linjun Zhang Ying Wei Li Tian James Zou Junzhou Huang Z. Li 87 84 0 26 Jul 2020
SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization A. Uddin Sirazam Monira Wheemyung Shin TaeChoong Chung Sung-Ho Bae 76 228 0 02 Jun 2020
Language Models are Few-Shot Learners Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan ... Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever Dario Amodei BDL 811 42,055 0 28 May 2020
YOLOv4: Optimal Speed and Accuracy of Object Detection Alexey Bochkovskiy Chien-Yao Wang H. Liao VLM ObjD 164 12,275 0 23 Apr 2020
Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning Zhiqiang Shen Zechun Liu Zhuang Liu Marios Savvides Trevor Darrell Eric P. Xing OCL SSL 70 103 0 11 Mar 2020
SuperMix: Supervising the Mixing Data Augmentation Ali Dabouei Sobhan Soleymani Fariborz Taherkhani Nasser M. Nasrabadi 72 100 0 10 Mar 2020
An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods Sanghyuk Chun Seong Joon Oh Sangdoo Yun Dongyoon Han Junsuk Choe Y. Yoo AAML OOD 399 53 0 09 Mar 2020
Dropout: Explicit Forms and Capacity Control R. Arora Peter L. Bartlett Poorya Mianjy Nathan Srebro 101 38 0 06 Mar 2020
DivideMix: Learning with Noisy Labels as Semi-supervised Learning Junnan Li R. Socher Guosheng Lin NoLa 105 1,030 0 18 Feb 2020
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence Kihyuk Sohn David Berthelot Chun-Liang Li Zizhao Zhang Nicholas Carlini E. D. Cubuk Alexey Kurakin Han Zhang Colin Raffel AAML 157 3,558 0 21 Jan 2020
GridMask Data Augmentation Pengguang Chen Shu Liu Hengshuang Zhao Xingquan Wang Jiaya Jia 94 311 0 13 Jan 2020
RandAugment: Practical automated data augmentation with a reduced search space E. D. Cubuk Barret Zoph Jonathon Shlens Quoc V. Le MQ 237 3,490 0 30 Sep 2019
Contrastive Multiview Coding Yonglong Tian Dilip Krishnan Phillip Isola SSL 169 2,403 0 13 Jun 2019
Augmenting Data with Mixup for Sentence Classification: An Empirical Study Hongyu Guo Yongyi Mao Richong Zhang 73 234 0 22 May 2019
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features Sangdoo Yun Dongyoon Han Seong Joon Oh Sanghyuk Chun Junsuk Choe Y. Yoo OOD 620 4,780 0 13 May 2019
MixMatch: A Holistic Approach to Semi-Supervised Learning David Berthelot Nicholas Carlini Ian Goodfellow Nicolas Papernot Avital Oliver Colin Raffel 145 3,029 0 06 May 2019
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition Daniel S. Park William Chan Yu Zhang Chung-Cheng Chiu Barret Zoph E. D. Cubuk Quoc V. Le VLM 177 3,461 0 18 Apr 2019
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations Dan Hendrycks Thomas G. Dietterich OOD VLM 174 3,435 0 28 Mar 2019
Robustness via curvature regularization, and vice versa Seyed-Mohsen Moosavi-Dezfooli Alhussein Fawzi J. Uesato P. Frossard AAML 77 319 0 23 Nov 2018
Data Augmentation using Random Image Cropping and Patching for Deep CNNs Ryo Takahashi Takashi Matsubara K. Uehara 65 331 0 22 Nov 2018
Exploring the Limits of Weakly Supervised Pretraining D. Mahajan Ross B. Girshick Vignesh Ramanathan Kaiming He Manohar Paluri Yixuan Li Ashwin R. Bharambe Laurens van der Maaten VLM 188 1,368 0 02 May 2018
Averaging Weights Leads to Wider Optima and Better Generalization Pavel Izmailov Dmitrii Podoprikhin T. Garipov Dmitry Vetrov A. Wilson FedML MoMe 135 1,662 0 14 Mar 2018