Learning Sparse Filters in Deep Convolutional Neural Networks with a l1/l2 Pseudo-Norm
July 20, 2020 ยท Declared Dead ยท ๐ ICPR Workshops
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Anthony Berthelier, Yongzhe Yan, Thierry Chateau, Christophe Blanc, Stefan Duffner, Christophe Garcia
arXiv ID
2007.10022
Category
cs.NE: Neural & Evolutionary
Cross-listed
cs.LG
Citations
11
Venue
ICPR Workshops
Last Checked
3 months ago
Abstract
While deep neural networks (DNNs) have proven to be efficient for numerous tasks, they come at a high memory and computation cost, thus making them impractical on resource-limited devices. However, these networks are known to contain a large number of parameters. Recent research has shown that their structure can be more compact without compromising their performance. In this paper, we present a sparsity-inducing regularization term based on the ratio l1/l2 pseudo-norm defined on the filter coefficients. By defining this pseudo-norm appropriately for the different filter kernels, and removing irrelevant filters, the number of kernels in each layer can be drastically reduced leading to very compact Deep Convolutional Neural Networks (DCNN) structures. Unlike numerous existing methods, our approach does not require an iterative retraining process and, using this regularization term, directly produces a sparse model during the training process. Furthermore, our approach is also much easier and simpler to implement than existing methods. Experimental results on MNIST and CIFAR-10 show that our approach significantly reduces the number of filters of classical models such as LeNet and VGG while reaching the same or even better accuracy than the baseline models. Moreover, the trade-off between the sparsity and the accuracy is compared to other loss regularization terms based on the l1 or l2 norm as well as the SSL, NISP and GAL methods and shows that our approach is outperforming them.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Neural & Evolutionary
R.I.P.
๐ป
Ghosted
R.I.P.
๐ป
Ghosted
Progressive Growing of GANs for Improved Quality, Stability, and Variation
R.I.P.
๐ป
Ghosted
Learning both Weights and Connections for Efficient Neural Networks
R.I.P.
๐ป
Ghosted
LSTM: A Search Space Odyssey
R.I.P.
๐ป
Ghosted
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
R.I.P.
๐ป
Ghosted
An Introduction to Convolutional Neural Networks
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted