DeepCache: Principled Cache for Mobile Deep Vision

MobiCom '18: The 24th Annual International Conference on Mobile Computing and Networking New Delhi India October, 2018, pp. 129-144, 2018.

Cited by: 34|Views80
EI
Weibo:
We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision

Abstract:

We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision. DeepCache benefits model execution efficiency by exploiting temporal locality in input video streams. It addresses a key challenge raised by mobile vision: the cache must operate under video scene variation, while trading off among cac...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments