Identification (biology)

Random variable

Random function

Pattern recognition (psychology)

Mathematics

Biology

Algorithm

Image (mathematics)

Statistics

Convolution random number generator

Pixel

Random forest

Artificial intelligence

Set (abstract data type)

Programming language

Geometry

Code (set theory)

Computer science

Botany

Object (grammar)

Rectangle

Process (computing)

Convolutional neural network

In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values. In this process, training images with various levels of occlusion are generated, which reduces the risk of over-fitting and makes the model robust to occlusion. Random Erasing is parameter learning free, easy to implement, and can be integrated with most of the CNN-based recognition models. Albeit simple, Random Erasing is complementary to commonly used data augmentation techniques such as random cropping and flipping, and yields consistent improvement over strong baselines in image classification, object detection and person re-identification. Code is available at: https://github.com/zhunzhong07/Random-Erasing.

Random Erasing Data Augmentation