Grad-FEC: Unequal Loss Protection of Deep Features in Collaborative Intelligence
This addresses communication reliability for edge-cloud AI deployments, but it is incremental as it builds on existing unequal loss protection techniques.
The paper tackles packet loss in collaborative intelligence systems by proposing Grad-FEC, an unequal loss protection method that selectively applies forward error correction to important feature packets, significantly improving system reliability and robustness.
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.