Striving for Simplicity: The All Convolutional Net

J. Springenberg, Alexey Dosovitskiy, Thomas Brox, M. Riedmiller
ICLR (workshop track), 2015
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.

Other associated files : striving_for_simplicity.pdf [4.2MB]  

Images and movies


BibTex reference

  author       = "J.T. Springenberg and A. Dosovitskiy and T. Brox and M. Riedmiller",
  title        = "Striving for Simplicity: The All Convolutional Net",
  booktitle    = "ICLR (workshop track)",
  year         = "2015",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2015/DB15a"

Other publications in the database