DFTS2: Simulating Deep Feature Transmission Over Packet Loss Channels
Published in
arXiv.org(2021)External Links:
TL
TL;DR
A simulation framework called DFTS2 is presented, which enables researchers to define the components of the CI system in TensorFlow~2, select a packet-based channel model with various parameters, and simulate system behavior under various channel conditions and error/loss control strategies.
Abstract
In edge-cloud collaborative intelligence (CI), an unreliable transmission channel exists in the information path of the AI model performing the inference. It is important to be able to simulate the performance of the CI system across an imperfect channel in order to understand system behavior and develop appropriate error control strategies. In this paper we present a simulation framework called DFTS2, which enables researchers to define the components of the CI system in TensorFlow~2, select a packet-based channel model with various parameters, and simulate system behavior under various channel conditions and error/loss control strategies. Using DFTS2, we also present the most comprehensive study to date of the packet loss concealment methods for collaborative image classification models.
References26 items
1
CALTEC: Content-Adaptive Linear Tensor Completion For Collaborative Intelligence
2
Latent Space Inpainting for Loss-Resilient Collaborative Object Detection
3
Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence
4
Collaborative Intelligence: Challenges and Opportunities
5