使用深度学习进行对象检测的数据增强 [英] Data Augmentation for Object Detection using Deep Learning

问题描述

我有一个关于数据增强的问题，用于训练用于对象检测的深度神经网络.

I have a question regarding data augmentation for training the deep neural network for object detection.

我的数据集非常有限(近300张图像).我通过将每个图像从0-360度旋转为15度的步长来扩充数据.因此，我只得到了24张旋转的图像.这样一来，我总共获得了约7200张图像.然后，我在每个增强图像中围绕感兴趣的对象绘制了一个边界框.

I have quite limited data set (nearly 300 images). I augmented the data by rotating each image from 0-360 degrees with stepsize of 15 degree. Consequently I got 24 rotated images out of just one. So in total, I got around 7200 images. Then I drew bounding box around the object of interest in each augmented image.

增强数据似乎是一种合理的方法吗?

Does it seem to be a reasonable approach to enhance the data?

最好的问候

推荐答案

要训练一个好的模型，您需要大量的代表数据.您的扩充仅代表旋转，因此，如果您担心对象旋转不足，这是个好方法.但是，从任何意义上讲，将其推广到其他对象/变换都无济于事.

In order to train a good model you need lots of representative data. Your augmentation is representative only for rotations, so yes, it is a good method, if you are concerned about having not enough object rotations. However, it will not help in any sense with generalization to other objects/transformations.

这篇关于使用深度学习进行对象检测的数据增强的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！