Fractional Max-Pooling

Code

• github.com/laplacetw/vgg-like-cifar10
  tf★ 7
• github.com/BendeguzToth/Fun-with-ConvNets
  none★ 0
• github.com/VladimirGol/KerasFractionalMaxPooling
  tf★ 0
• github.com/JonasWechsler/DeepLearningLab5
  tf★ 0

Abstract

Convolutional networks almost always incorporate some form of spatial pooling, and very often it is alpha times alpha max-pooling with alpha=2. Max-pooling act on the hidden layers of the network, reducing their size by an integer multiplicative factor alpha. The amazing by-product of discarding 75% of your data is that you build into the network a degree of invariance with respect to translations and elastic distortions. However, if you simply alternate convolutional layers with max-pooling layers, performance is limited due to the rapid reduction in spatial size, and the disjoint nature of the pooling regions. We have formulated a fractional version of max-pooling where alpha is allowed to take non-integer values. 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: for instance, we improve on the state-of-the art for CIFAR-100 without even using dropout.

Tasks

Benchmark Results

Reproductions