How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization

12 October 2022

Papers citing "How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization"

22 / 22 papers shown

Title
Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data Sreyan Ghosh Sonal Kumar Zhifeng Kong Rafael Valle Bryan Catanzaro Dinesh Manocha DiffM 92 3 0 02 Oct 2024
On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification Sanyam Kapoor Wesley J. Maddox Pavel Izmailov A. Wilson BDL UD 61 51 0 30 Mar 2022
A Data-Augmentation Is Worth A Thousand Samples: Exact Quantification From Analytical Augmented Sample Moments Randall Balestriero Ishan Misra Yann LeCun 57 20 0 16 Feb 2022
Patches Are All You Need? Asher Trockman J. Zico Kolter ViT 252 410 0 24 Jan 2022
Swin Transformer V2: Scaling Up Capacity and Resolution Ze Liu Han Hu Yutong Lin Zhuliang Yao Zhenda Xie ... Yue Cao Zheng Zhang Li Dong Furu Wei B. Guo ViT 205 1,809 0 18 Nov 2021
ResNet strikes back: An improved training procedure in timm Ross Wightman Hugo Touvron Hervé Jégou AI4TS 242 494 0 01 Oct 2021
Stochastic Training is Not Necessary for Generalization Jonas Geiping Micah Goldblum Phillip E. Pope Michael Moeller Tom Goldstein 131 75 0 29 Sep 2021
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers Andreas Steiner Alexander Kolesnikov Xiaohua Zhai Ross Wightman Jakob Uszkoreit Lucas Beyer ViT 107 632 0 18 Jun 2021
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization Kartik Ahuja Ethan Caballero Dinghuai Zhang Jean-Christophe Gagnon-Audet Yoshua Bengio Ioannis Mitliagkas Irina Rish OOD 57 268 0 11 Jun 2021
Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error Stanislav Fort Andrew Brock Razvan Pascanu Soham De Samuel L. Smith 50 32 0 27 May 2021
Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data Marc Finzi Samuel Stanton Pavel Izmailov A. Wilson 116 323 0 25 Feb 2020
General $E(2)$ -Equivariant Steerable CNNs Maurice Weiler Gabriele Cesa 100 524 0 19 Nov 2019
RandAugment: Practical automated data augmentation with a reduced search space E. D. Cubuk Barret Zoph Jonathon Shlens Quoc V. Le MQ 217 3,485 0 30 Sep 2019
Further advantages of data augmentation on convolutional neural networks Alex Hernández-García Peter König 55 108 0 26 Jun 2019
AutoAugment: Learning Augmentation Policies from Data E. D. Cubuk Barret Zoph Dandelion Mané Vijay Vasudevan Quoc V. Le 118 1,771 0 24 May 2018
A Kernel Theory of Modern Data Augmentation Tri Dao Albert Gu Alexander J. Ratner Virginia Smith Christopher De Sa Christopher Ré 98 193 0 16 Mar 2018
Three Factors Influencing Minima in SGD Stanislaw Jastrzebski Zachary Kenton Devansh Arpit Nicolas Ballas Asja Fischer Yoshua Bengio Amos Storkey 76 463 0 13 Nov 2017
Improving Deep Learning using Generic Data Augmentation Luke Taylor G. Nitschke 47 383 0 20 Aug 2017
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era Chen Sun Abhinav Shrivastava Saurabh Singh Abhinav Gupta VLM 182 2,397 0 10 Jul 2017
Geometry of Optimization and Implicit Regularization in Deep Learning Behnam Neyshabur Ryota Tomioka Ruslan Salakhutdinov Nathan Srebro AI4CE 65 133 0 08 May 2017
ImageNet Large Scale Visual Recognition Challenge Olga Russakovsky Jia Deng Hao Su J. Krause S. Satheesh ... A. Karpathy A. Khosla Michael S. Bernstein Alexander C. Berg Li Fei-Fei VLM ObjD 1.7K 39,509 0 01 Sep 2014
SMOTE: Synthetic Minority Over-sampling Technique Nitesh Chawla Kevin W. Bowyer Lawrence Hall W. Kegelmeyer AI4TS 355 25,621 0 09 Jun 2011