使用 CNN 进行二元图像分类 - 选择“负"的最佳实践数据集? [英] Binary Image Classification with CNN - best practices for choosing "negative" dataset?

问题描述

比如说，我想训练一个 CNN 来检测图像是否是汽车.

Say, I want to train a CNN to detect whether an image is a car or not.

选择Not-Car"数据集的最佳实践或方法有哪些?

What are some best practices or methods to choosing the "Not-Car" dataset?

因为这个数据集可能是无限的(基本上不是汽车的任何东西) - 是否有关于数据集需要多大的指导方针?它们是否应该包含与汽车非常相似但又不是(飞机、船只等)的对象?

Because this dataset could potentially be infinite (basically anything that is not a car) - is there a guideline on how big the dataset needs to be? Should they contain objects which are very similar to cars, but are not (planes, boats, etc.)?

推荐答案

与所有监督式机器学习一样，训练集应该反映模型将要使用的真实分布.神经网络基本上是一个函数逼近器.您的实际目标是近似真实世界的分布，但在实践中只能从中获取样本，而这个样本是神经网络唯一会看到的.对于训练流形之外的任何输入方式，输出将只是一个猜测(另见关于 AI.SE 的讨论).

Like in all of supervised machine learning, the training set should reflect the real distribution that the model is going to work with. Neural network is basically a function approximator. Your actual goal is to approximate the real-world distribution, but in practice it's only possible to get the sample from it, and this sample is the only thing a neural network will see. For any input way outside of the training manifold, the output will be a just a guess (see also this discussion on AI.SE).

因此，在选择否定数据集时，您应该回答的第一个问题是:该模型的可能用例是什么?例如，如果您正在为智能手机构建应用程序，那么负样本可能应该包括街景、建筑物和商店的图片、人物、室内环境等. 智能手机相机拍摄的图像不太可能是野生动物或抽象画，也就是说，它是你现实中不太可能的输入分布.

So when choosing a negative dataset, the first question you should answer is: What will be the likely use-case of this model? E.g., if you're building an app for a smartphone, then the negative sample should probably include street views, pictures of buildings and stores, people, indoor environment, etc. It's unlikely that the image from the smartphone camera will be a wild animal or abstract painting, i.e., it's an improbable input in your real distribution.

包括看起来像正类的图像(卡车、飞机、船等)是个好主意，因为低转换层的特征(边缘、角落)将非常相似，神经网络学习很重要重要的高级功能正确.

Including images that look like a positive class (trucks, airplanes, boats, etc) is a good idea, because the low-conv-layer features (edges, corners) will be very similar and it's important that the neural network learned important high-level features correctly.

一般来说，我会使用比正面图片多 5-10 倍的负面图片.CIFAR-10 是一个很好的起点:50000 张训练图像中有 5000 张是汽车，5000 是飞机，等等.事实上，建立一个 10 级分类器并不是一个坏主意.在这种情况下，您将通过阈值处理推断类是汽车的确定性，将此 CNN 转换为二元分类器.CNN 不确定的任何内容都将被解释为不是汽车.

In general, I'd use 5-10x more negative images that positive ones. CIFAR-10 is a good starting point: out of 50000 training images 5000 are the cars, 5000 are the planes, etc. In fact, building a 10-class classifier is not a bad idea. In this case, you'll transform this CNN to a binary classifier by thresholding its certainty that the inferred class is a car. Anything that the CNN isn't certain about will be interpreted as not a car.

这篇关于使用 CNN 进行二元图像分类 - 选择“负"的最佳实践数据集?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！