Striving for Simplicity: The All Convolutional Net

Most modern <PRE_TAG>convolutional neural networks (CNNs)</POST_TAG> used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state of the art for object recognition from small images with convolutional networks, questioning the necessity of different components in the pipeline. We find that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks. Following this finding -- and building on other recent work for finding simple network structures -- we propose a new architecture that consists solely of <PRE_TAG>convolutional layers</POST_TAG> and yields competitive or state of the art performance on several object recognition datasets (CIFAR-10, CIFAR-100, ImageNet). To analyze the network we introduce a new variant of the "de<PRE_TAG>convolution approach</POST_TAG>" for visualizing features learned by CNNs, which can be applied to a broader range of network structures than existing approaches.