Grad-FEC: Unequal Loss Protection of Deep Features in Collaborative Intelligence

Collaborative intelligence (CI) involves dividing an artificial intelligence (AI) model into two parts: front-end, to be deployed on an edge device, and back-end, to be deployed in the cloud. The deep feature tensors produced by the front-end are transmitted to the cloud through a communication chan...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Image Processing (ICIP) pp. 3140 - 3144
Main Authors Uyanik, Korcan, Yeganli, S. Faegheh, Bajic, Ivan V.
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.10.2023
Subjects
Collaborative intelligence
Communication channels
deep feature transmission
Estimation
Forward error correction
Grad-CAM
Image processing
loss/error resilience
Packet loss
Robustness
Tensors
Online AccessGet full text

Cover

More Information
Summary:Collaborative intelligence (CI) involves dividing an artificial intelligence (AI) model into two parts: front-end, to be deployed on an edge device, and back-end, to be deployed in the cloud. The deep feature tensors produced by the front-end are transmitted to the cloud through a communication channel, which may be subject to packet loss. To address this issue, in this paper, we propose a novel approach to enhance the resilience of the CI system in the presence of packet loss through Unequal Loss Protection (ULP). The proposed ULP approach involves a feature importance estimator, which estimates the importance of feature packets produced by the front-end, and then selectively applies Forward Error Correction (FEC) codes to protect important packets. Experimental results demonstrate that the proposed approach can significantly improve the reliability and robustness of the CI system in the presence of packet loss.
DOI:10.1109/ICIP49359.2023.10222115