Striving for Simplicity: The All Convolutional Net

Abstract

Most modern convolutional neural networks (CNNs) 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 convolutional layers 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 "deconvolution approach" for visualizing features learned by CNNs, which can be applied to a broader range of network structures than existing approaches.

accepted to ICLR-2015 workshop track; no changes other than style

References in corpus (7)

• Improving neural networks by preventing co-adaptation of feature detectors
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Going Deeper with Convolutions
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• Fractional Max-Pooling
• High-Performance Neural Networks for Visual Object Classification
• Deep Networks with Internal Selective Attention through Feedback Connections