Grad-FEC: Unequal Loss Protection of Deep Features in Collaborative Intelligence (2307.01846v1)
Abstract: Collaborative intelligence (CI) involves dividing an 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.
- “Neurosurgeon: Collaborative intelligence between the cloud and mobile edge,” in Proc. 22nd ACM Int. Conf. Arch. Support Programming Languages and Operating Syst., 2017, pp. 615–629.
- “Collaborative intelligence: Challenges and opportunities,” in Proc. IEEE ICASSP, 2021, pp. 8493–8497.
- “Toward intelligent sensing: Intermediate deep feature compression,” IEEE Transactions on Image Processing, vol. 29, pp. 2230–2243, 2020.
- “Neural joint source-channel coding,” in Proc. ICML, 2019.
- “BottleNet++: An end-to-end approach for feature compression in device-edge co-inference systems,” in Proc. IEEE ICC Workshops, 2020, pp. 1–6.
- “Tensor completion methods for collaborative intelligence,” IEEE Access, vol. 8, pp. 41162–41174, 2020.
- I. V. Bajić, “Latent space inpainting for loss-resilient collaborative object detection,” in Proc. IEEE ICC, 2021, pp. 1–6.
- “CALTeC: Content-adaptive linear tensor completion for collaborative intelligence,” in Proc. IEEE ICIP, 2021.
- “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” in Proc. IEEE ICCV, 2017, pp. 618–626.
- “Deep residual learning for image recognition,” in Proc. IEEE CVPR, 2016, pp. 770–778.
- “Unequal loss protection: graceful degradation of image quality over packet erasure channels through forward error correction,” IEEE J. Selected Areas in Communications, vol. 18, no. 6, pp. 819–828, 2000.
- M. van der Schaar and H. Radha, “Unequal packet loss resilience for fine-granular-scalability video,” IEEE Trans. Multimedia, vol. 3, no. 4, pp. 381–394, 2001.
- “Unequal loss protection for robust transmission of motion compensated video over the internet,” Signal Processing: Image Communication, vol. 18, no. 3, pp. 157–167, 2003.
- Error Control Coding, Pearson, 2nd edition, 2004.
- L. Rizzo, “Effective erasure codes for reliable computer communication protocols,” SIGCOMM Comput. Commun. Rev., vol. 27, no. 2, pp. 24–36, Apr. 1997 1997.
- “Imagenet large scale visual recognition challenge,” Int. J. Comput. Vision, vol. 115, no. 3, pp. 211–252, Dec. 2015.
- “Adam: A method for stochastic optimization,” in Proc. ICLR, 2015.