Image Data Augmentation

Edit

Computer Vision • 45 methods

Image Data Augmentation refers to a class of methods that augment an image dataset to increase the effective size of the training set, or as a form of regularization to help the network learn more effective representations.

Subcategories

1 Adversarial Image Data Augmentation

Methods

Add a Method

Method	Year	Papers
Mixup mixup: Beyond Empirical Risk Minimization	2017	541
GPS Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation	2020	520
Random Resized Crop	2000	268
ColorJitter	2000	224
Random Gaussian Blur	2000	222
CutMix CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features	2019	177
Random Horizontal Flip	2000	78
Cutout Improved Regularization of Convolutional Neural Networks with Cutout	2017	60
RandAugment RandAugment: Practical automated data augmentation with a reduced search space	2019	58
AutoAugment AutoAugment: Learning Augmentation Policies from Data	2018	57
ADA Training Generative Adversarial Networks with Limited Data	2020	49
Copy-Paste Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation	2020	33
AugMix AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty	2019	16
Random Erasing Random Erasing Data Augmentation	2017	14
APA Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data	2021	13
Random Scaling	2000	10
Image Scale Augmentation	2000	9
PAA Local Patch AutoAugment with Multi-Agent Collaboration	2021	8
Fast AutoAugment Fast AutoAugment	2019	6
DG-Net Joint Discriminative and Generative Learning for Person Re-identification	2019	4
DiffAugment Differentiable Augmentation for Data-Efficient GAN Training	2020	3
Random Grayscale	2000	3
Adversarial Color Enhancement Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter	2020	3
GridMask GridMask Data Augmentation	2020	3
Population Based Augmentation Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules	2019	3
LFPNet (TTA) $F$, $B$, Alpha Matting	2020	2
MaxUp MaxUp: A Simple Way to Improve Generalization of Neural Network Training	2020	2
Local Mixup Preventing Manifold Intrusion with Locality: Local Mixup	2022	2
FMix FMix: Enhancing Mixed Sample Data Augmentation	2020	2
SuperpixelGridMasks	2000	2
3-Augment DeiT III: Revenge of the ViT	2022	1
InstaBoost InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting	2019	1
R-Mix Expeditious Saliency-guided Mix-up through Random Gradient Thresholding	2022	1
Handwritten OCR Handwritten image augmentation	2023	1
OA-Mix Object-Aware Domain Generalization for Object Detection	2023	1
Sample Redistribution Sample and Computation Redistribution for Efficient Face Detection	2021	1
Batchboost batchboost: regularization for stabilizing training with resistance to underfitting & overfitting	2020	1
Object Dropout Perturb, Predict & Paraphrase: Semi-Supervised Learning using Noisy Student for Image Captioning	2021	1
CutBlur Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy	2020	1
RandomRotate	2000	1
imagemorph	2000	0

Image Data Augmentation Edit

Methods Add a Method

Image Data Augmentation

Edit

Methods

Add a Method