Name
Title | ||
|---|---|---|
Fixed-Point Quantization of 3D Convolutional Neural Networks for Energy-Efficient Action Recognition |
Abstract | ||
|---|---|---|
In this paper, 3D convolutional neural networks (CNNs) are simplified to reduce the energy consumption of the action recognition process. Instead of using floating-point weights and input values, which results in a huge amount of processing energy, we introduce a systematic way to quantize all the values of 3D CNNs without degrading the recognition accuracy. Simulation results show that, compared to the baseline CNN architecture, the proposed method significantly reduces the computational complexity as well as the memory requirements. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/ISOCC.2018.8649987 | 2018 International SoC Design Conference (ISOCC) |
Keywords | Field | DocType |
Three-dimensional displays,Quantization (signal),Convolutional neural networks,Memory management,Optimization,Complexity theory,Energy efficiency | Convolutional neural network,Efficient energy use,Computer science,Action recognition,Electronic engineering,Memory management,Fixed point,Quantization (signal processing),Computer engineering,Energy consumption,Computational complexity theory | Conference |
ISSN | ISBN | Citations |
2163-9612 | 978-1-5386-7960-9 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hyunhoon Lee | 1 | 0 | 0.34 |
| Younghoon Byun | 2 | 6 | 3.21 |
| Seokha Hwang | 3 | 0 | 1.01 |
| Sunggu Lee | 4 | 478 | 41.40 |
| Youngjoo Lee | 5 | 74 | 18.85 |