(2014. 12) Fractional Max-pooling
Last updated
Last updated
Submitted on 2014. 12
Benjamin Graham
Our version of max-pooling is stochastic as there are lots of different ways of constructing suitable pooling regions. We find that our form of fractional max-pooling reduces overfitting on a variety of datasets.
Spatial pooling layers are building blocks for Convolutional Neural Networks (CNNs).
Max Pooling 2x2
Pros:
Fast.
Quickly reduces the size of the hidden layer.
Encodes a degree of invariance with respect to translations and elastic distortions.
Cons:
Disjoint nature of pooling regions.
Since size decreases rapidly, stacks of back-to-back CNNs are needed to build deep networks.
Fractional Max-Pooling
Reduces the spatial size of the image by a factor of α, where α ∈ (1, 2).
Introduces randomness in terms of choice of pooling region.
Pooling regions can be chosen in a random or pseudorandom manner.
Pooling regions can be disjoint or overlapping.
Random FMP is good on its own but may underfit when combined with dropout or training data augmentation.