Evaluation of Deep Neural Network Compression Methods for Edge Devices Using Weighted Score-Based Ranking Scheme
The demand for object detection capability in edge computing systems has surged. As such, the need for lightweight Convolutional Neural Network (CNN)-based object detection models has become a focal point. Current models are large in memory and deployment in edge devices is demanding. This shows tha...
Guardado en:
Autores principales: | Olutosin Ajibola Ademola, Mairo Leier, Eduard Petlenkov |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/348a22621e7447a08b4c016aa14abe64 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Characterization of Full Pore and Stress Compression Response of Reservoirs With Different Coal Ranks
por: Jielin Lu, et al.
Publicado: (2021) -
FPGA compression of ECG signals by using modified convolution scheme of the Discrete Wavelet Transform
por: Ballesteros,Dora M, et al.
Publicado: (2012) -
Formation of biliodigestive anastomoses with the TiNi compression device
por: G. T. Dambaev, et al.
Publicado: (2018) -
Pressure Adaptations in Deep-Sea <i>Moritella</i> Dihydrofolate Reductases: Compressibility versus Stability
por: Ryan W. Penhallurick, et al.
Publicado: (2021) -
Comparison between Impact Factor, Eigenfactor Score, and SCImago Journal Rank Indicator in Anatomy and Morphology Journals
por: Cantín,Mario, et al.
Publicado: (2015)