Sorted Pooling in Convolutional Networks for One-shot Learning
share
We present generalized versions of the commonly used maximum pooling operation: kth maximum and sorted pooling operations which selects the kth largest response in each pooling region, selecting locally consistent features of the input images. This method is able to increase the generalization power of a network and can be used to decrease training time and error rate of networks and it can significantly improve accuracy in case of training scenarios where the amount of available data is limited, like one-shot learning scenarios
READ FULL TEXT