computer-vision-10
Image Augmentation
3260 papers • 126 benchmarks • 313 datasets
Image Augmentation is a data augmentation method that generates more training data from the existing training samples. Image Augmentation is especially useful in domains where training data is limited or expensive to obtain like in biomedical applications. Source: Improved Image Augmentation for Convolutional Neural Networks by Copyout and CopyPairing ( Image credit: Kornia )
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in image-augmentation-32
Trend
Dataset
Best Model
Actions
Intel Image Classification
Intel Image Classification
Libraries
iUse these libraries to find image-augmentation-32 models and implementations
2 papers 38,163
Datasets
Subtasks
No subtasks available.
Most implemented papers
AutoAugment: Learning Augmentation Policies from Data
Quoc V. Le, E. D. Cubuk, Dandelion Mané, Vijay Vasudevan, Barret Zoph•Wed May 23 2018
This paper describes a simple procedure called AutoAugment to automatically search for improved data augmentation policies, which achieves state-of-the-art accuracy on CIFAR-10, CIFar-100, SVHN, and ImageNet (without additional data).
1927