Explore Courses Blog Tutorials Interview Questions
0 votes
in AI and Deep Learning by (50.2k points)

I would very much like to understand how I can enrich a CNN with provided meta information. As I understand, a CNN 'just' looks at the images and classifies it into objects without looking at possibly existing meta-parameters such as time, weather conditions, etc.

To be more precise, I am using a Keras CNN with TensorFlow in the backend. I have the typical Conv2D and MaxPooling Layers and a fully connected model at the end of the pipeline. It works nicely and gives me good accuracy. However, I do have additional meta information for each image (the manufacturer of the camera with which the image was taken) that is unused so far.

What is a recommended way to incorporate this meta-information into the model? I could not yet come out with a good solution by myself.

Thanks for any help!

1 Answer

0 votes
by (108k points)

Normally, it is accomplished by adding this information to one of the fully connected layers before the prediction. The fully connected layer gives you a 'K' number of features representing your image, you just concatenate them with the additional information you have.

If you have K features representing the image + 1 meta information. This would mean your fully connected layer had K+1 input nodes, one of them being the meta-information.

Just think of the Convolutional Neural Network "before" the fully connected layers as a means to extract features of the images. Later in the fully connected layers, these features are used together for the classification.

Welcome to Intellipaat Community. Get your technical queries answered by top developers!

30.7k questions

32.8k answers


109k users

Browse Categories