English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

Implicit Filter Sparsification In Convolutional Neural Networks

MPS-Authors
/persons/resource/persons129023

Mehta,  Dushyant
Computer Graphics, MPI for Informatics, Max Planck Society;

/persons/resource/persons45610

Theobalt,  Christian
Computer Graphics, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1905.04967.pdf
(Preprint), 236KB

Supplementary Material (public)
There is no public supplementary material available
Citation

Mehta, D., Kim, K. I., & Theobalt, C. (2019). Implicit Filter Sparsification In Convolutional Neural Networks. Retrieved from http://arxiv.org/abs/1905.04967.


Cite as: http://hdl.handle.net/21.11116/0000-0003-FE07-8
Abstract
We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay. Through an extensive empirical study (Mehta et al., 2019) we hypothesize the mechanism behind the sparsification process, and find surprising links to certain filter sparsification heuristics proposed in literature. Emergence of, and the subsequent pruning of selective features is observed to be one of the contributing mechanisms, leading to feature sparsity at par or better than certain explicit sparsification / pruning approaches. In this workshop article we summarize our findings, and point out corollaries of selective-featurepenalization which could also be employed as heuristics for filter pruning