DFTS: Deep Feature Transmission Simulator

Peer reviewed: 
Yes, item is peer reviewed.
Scholarly level: 
Graduate student (PhD)
Final version published as: 

H. Unnibhavi, H. Choi, S. R. Alvar, and I. V. Bajic, "DFTS: Deep Feature Transmission Simulator," IEEE Multimedia Signal Processing Workshop (MMSP), Vancouver, BC, Aug. 2018.

Date created: 
2018-06-22
Keywords: 
Collaborative intelligence
deep feature transmission
quantization
packet loss
Abstract: 

Collaborative intelligence is a deployment paradigm for deep AI models where some of the layers run on the mobile terminal or network edge, while others run in the cloud. In this scenario, features computed in the model need to be transferred between the edge and the cloud over an imperfect channel. Here we present a simulator to help study the effects of imperfect packet-based transmission of deep features. Our simulator is implemented in Keras and allows users to study the effects of both lossy packet transmission and quantization on the accuracy.

Language: 
English
Document type: 
Conference presentation
File(s): 
Statistics: