Exploiting Symmetries Of Distributions In Cnns And Folded Coding
Keywords
Activation Functions; Coding; Convolutional Neural Networks; Distribution Estimation; Symmetry
Abstract
We introduce the concept of Folded Coding' for continuous univariate distributions estimating the distribution and coding the samples simultaneously. Folded Coding assumes symmetries in the distribution and requires significantly fewer parameters compared to conventional models when the symmetry assumption is satisfied. We incorporate the mechanics of Folded Coding into Convolutional Neural Networks (CNN) in the form of layers referred to as Binary Expanded ReLU (BEReLU) Shared Convolutions and Instance Fully Connected (I-FC). BEReLU and I-FC force the network to have symmetric functionality in the space of samples. Therefore similar patterns of prediction are applied to sections of the space where the model does not have observed samples. We experimented with BEReLU on generic networks using different parameter sizes on CIFAR-10 and CIFAR-100. Our experiments show increased accuracy of the models equipped with the BEReLU layer when there are fewer parameters. The performance of the models with BEReLU layer remains similar to original network with the increase of parameter number. The experiments provide further evidence that estimation of distribution symmetry is part of CNNs' functionality.
Publication Date
12-13-2018
Publication Title
Proceedings - 2018 15th Conference on Computer and Robot Vision, CRV 2018
Number of Pages
47-54
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CRV.2018.00017
Copyright Status
Unknown
Socpus ID
85060526937 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85060526937
STARS Citation
Marvasti, Ehsan Emad; Marvasti, Amir Emad; and Foroosh, Hassan, "Exploiting Symmetries Of Distributions In Cnns And Folded Coding" (2018). Scopus Export 2015-2019. 10101.
https://stars.library.ucf.edu/scopus2015/10101