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.

Keywords

Convolutional neural networkPoolingComputer scienceConvolution (computer science)Pipeline (software)Artificial intelligenceDeconvolutionPattern recognition (psychology)Net (polyhedron)Object (grammar)Cognitive neuroscience of visual object recognitionContextual image classificationLayer (electronics)Image (mathematics)AlgorithmArtificial neural networkMathematics

Affiliated Institutions

University of Freiburg DE

Related Publications

Learning Deconvolution Network for Semantic Segmentation

Hyeonwoo Noh , Seunghoon Hong , Bohyung Han

We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer ne...

2015 3978 citations

Network In Network

Min Lin , Qiang Chen , Shuicheng Yan

Abstract: We propose a novel deep network structure called In Network (NIN) to enhance model discriminability for local patches within the receptive field. The conventional con...

2014 arXiv (Cornell University) 1037 citations

Fractional Max-Pooling

Benjamin Graham

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 lay...

2014 arXiv (Cornell University) 335 citations

Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition

Ossama Abdel‐Hamid , Abdelrahman Mohamed , Hui Jiang +1 more

Convolutional Neural Networks (CNN) have showed success in achieving translation invariance for many image processing tasks. The success is largely attributed to the use of loca...

2012 885 citations

Learning Deep Features for Discriminative Localization

Bolei Zhou , Aditya Khosla , Àgata Lapedriza +2 more

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable...

2016 10334 citations

Publication Info

Year: 2014
Type: preprint
Citations: 2592
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Striving for Simplicity: The All Convolutional Net

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

2592

OpenAlex

Cite This

APA Style

                            
                                    Jost Tobias Springenberg, 
                                
                                    Alexey Dosovitskiy, 
                                
                                    Thomas Brox
                                
                                et al.
                            
                            (2014). 
                            Striving for Simplicity: The All Convolutional Net. 
                            arXiv (Cornell University)
                            
                            .
                            https://doi.org/10.48550/arxiv.1412.6806

Identifiers

DOI: 10.48550/arxiv.1412.6806