Striving for Simplicity: The All Convolutional Net. Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. arXiv:1412.6806 [cs], December, 2014. arXiv: 1412.6806
Striving for Simplicity: The All Convolutional Net [link]Paper  abstract   bibtex   
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.
@article{springenberg_striving_2014,
	title = {Striving for {Simplicity}: {The} {All} {Convolutional} {Net}},
	shorttitle = {Striving for {Simplicity}},
	url = {http://arxiv.org/abs/1412.6806},
	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.},
	language = {en},
	urldate = {2019-03-03},
	journal = {arXiv:1412.6806 [cs]},
	author = {Springenberg, Jost Tobias and Dosovitskiy, Alexey and Brox, Thomas and Riedmiller, Martin},
	month = dec,
	year = {2014},
	note = {arXiv: 1412.6806},
	keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing},
}

Downloads: 0