Sorted Pooling in Convolutional Networks for One-shot Learning
This work addresses data scarcity in one-shot learning scenarios, offering an incremental improvement over existing pooling methods.
The authors tackled the problem of limited data in one-shot learning by introducing sorted pooling operations, which select the kth largest response in pooling regions to improve generalization, resulting in decreased training time and error rates with significant accuracy improvements.
We present generalized versions of the commonly used maximum pooling operation: $k$th maximum and sorted pooling operations which selects the $k$th 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