现在的CNN（卷积神经网络）作为DetectNet旋转不变吗？ [英] Are modern CNN (convolutional neural network) as DetectNet rotate invariant?

问题描述

众所周知，用于对象检测的nVidia DetectNet - CNN（卷积神经网络）基于来自Yolo / DenseBox的方法：

现在的CNN（卷积神经网络）作为DetectNet旋转不变吗？

我可以训练DetectNet在成千上万个不同的图像与一个相同的旋转角度的对象，以检测任何旋转角度的对象？

旋转不变的：Yolo，Yolo v2，DenseBox基于哪个DetectNet？

解决方案

否

CNN不旋转不变。

您可以训练CNN将图像分类到预定义的类别中（如果要检测多个对象

在您的示例中，您需要使用分类器扫描图像的每个地方。

CNN对于训练数据中的小水平或垂直运动是不变的。 / p>

As known nVidia DetectNet - CNN (convolutional neural network) for object detection is based on approach from Yolo/DenseBox: https://devblogs.nvidia.com/parallelforall/deep-learning-object-detection-digits/

DetectNet is an extension of the popular GoogLeNet network. The extensions are similar to approaches taken in the Yolo and DenseBox papers.

And as shown here, DetectNet can detects objects (cars) with any rotations: https://devblogs.nvidia.com/parallelforall/detectnet-deep-neural-network-object-detection-digits/

Are modern CNN (convolutional neural network) as DetectNet rotate invariant?

Can I train DetectNet on thousands different images with one the same rotation angle of object, to detect objects on any rotation angles?

And what about rotate invariant of: Yolo, Yolo v2, DenseBox on which based DetectNet?

解决方案

No

CNNs are not rotate invariant. You need to include in your training set images with every possible rotation.

You can train a CNN to classify images into predefined categories (if you want to detect several objects in a image as in your example you need to scan every place of a image with your classifier).

A CNN is invariant to small horizontal or vertical movements in your training data.

这篇关于现在的CNN（卷积神经网络）作为DetectNet旋转不变吗？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！