Solved – minimum image size for successful deep auto-encoders

autoencodersclassificationdeep learningimage processingmachine learning

Deep auto-encoders has been successfully used for problems like digit classification. In this example,

enter image description here

images with 28×28 pixels have been classified into digit 0-9. And the feature vector size is 28x28x1 = 784×1. For my understanding, the CNN based deep learning do require the image size to be relatively 'large' because the smallest sliding window can be 3×3, and if the image or image patch is very small, the sliding window will not work.

I am wondering if deep auto-encoders can cope with image with very small size. For example, if we have digit images with 8×8 pixels instead of 28×28 pixels, will us be able to train the deep auto-encoders? And is there a minimum image size for successful deep auto-encoders?

Thanks. A.

Best Answer

There is not really a minimum size. If the input is small enough you won't need to use a convolutional neural network. You can make a deep purely feed-forward auto-encoder. (Sometimes feed-forward networks are referred to as fully-connected convolutional layers.)

Related Question