Name
Title | ||
|---|---|---|
Guaranteed Compression Rate for Activations in CNNs using a Frequency Pruning Approach |
Abstract | ||
|---|---|---|
Convolutional Neural Networks have become state of the art for many computer vision tasks. However, the size of Neural Networks prevents their application in resource constrained systems. In this work, we present a lossy compression technique for intermediate results of Convolutional Neural Networks. The proposed method offers guaranteed compression rates and additionally adapts to performance requirements. Our experiments with networks for classification and semantic segmentation show, that our method outperforms state-of-the-art compression techniques used in CNN accelerators. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.23919/DATE.2019.8715210 | 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE) |
Keywords | Field | DocType |
Deep Neural Networks,Convolutional Neural Networks,Compression,Embedded Systems | Data compression ratio,Computer science,Parallel computing,Pruning | Conference |
ISSN | ISBN | Citations |
1530-1591 | 978-1-7281-0331-0 | 0 |
PageRank | References | Authors |
0.34 | 3 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sebastian Vogel | 1 | 23 | 5.63 |
| Christoph Schorn | 2 | 5 | 2.74 |
| Andre Guntoro | 3 | 20 | 11.05 |
| Gerd Ascheid | 4 | 1205 | 144.76 |