Ordinal Pooling Networks: For Preserving Information over Shrinking Feature Maps

04/08/2018
by   Ashwani Kumar, et al.
0

In the framework of convolutional neural networks that lie at the heart of deep learning, downsampling is often performed with a max-pooling operation that however completely discards the information from other activations in a pooling region. To address this issue, a novel pooling scheme, Ordinal Pooling Network (OPN), is introduced in this work. OPN rearranges all the elements of a pooling region in a sequence and assigns different weights to all the elements based upon their orders in the sequence, where the weights are learned via the gradient-based optimisation. The results of our small-scale experiments on image classification task on MNIST database demonstrate that this scheme leads to a consistent improvement in the accuracy over max-pooling operation. This improvement is expected to increase in the deep networks, where several layers of pooling become necessary.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset