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.
In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch.
Ranked #3 on Image Classification on SVHN
In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).
Ranked #3 on Image Classification on Fashion-MNIST
We provide examples of image augmentations for different computer vision tasks and show that Albumentations is faster than other commonly used image augmentation tools on the most of commonly used image transformations.
Importantly, the best policy found on COCO may be transferred unchanged to other detection datasets and models to improve predictive accuracy.
Ranked #14 on Object Detection on PASCAL VOC 2007
There is large consent that successful training of deep networks requires many thousand annotated training samples.
Ranked #1 on Cell Segmentation on DIC-HeLa
CELL SEGMENTATION COLORECTAL GLAND SEGMENTATION: ELECTRON MICROSCOPY IMAGE SEGMENTATION IMAGE AUGMENTATION LESION SEGMENTATION LUNG NODULE SEGMENTATION MULTI-TISSUE NUCLEUS SEGMENTATION PANCREAS SEGMENTATION RETINAL VESSEL SEGMENTATION SEMANTIC SEGMENTATION SKIN CANCER SEGMENTATION
In this work, we present a new perspective on how to effectively noise unlabeled examples and argue that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning.
Ranked #1 on Sentiment Analysis on Amazon Review Full
In this paper, we present an improved deep learning-based end to end approach for solving both problems of table detection and structure recognition using a single Convolution Neural Network (CNN) model.
Ranked #1 on Table Detection on ICDAR2013
A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations.
Ranked #6 on Image Classification on SVHN
Our work is motivated by the intriguing property that deep networks are surprisingly good at linearizing features, such that certain directions in the deep feature space correspond to meaningful semantic transformations, e. g., adding sunglasses or changing backgrounds.