Not All Split Points Are Created Equal
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Split inference enables deep neural networks to be partitioned between edge devices and servers. However, most prior work examines only a narrow set of split points and overlooks the trade-off between computational offload and feature compressibility. This paper introduces a framework for systematically analyzing split points across an entire backbone, evaluating both compute distribution and compression efficiency. Results show that later layers offer significantly higher compressibility, achieving BD-Rate reductions of up to 57% compared to remote inference, while earlier and mid-level layers provide greater compute offload for the edge device. A saturation effect is observed in very deep layers, where further gains diminish. These findings demonstrate that optimal split points depend on jointly balancing compute and compression, and the proposed framework provides a foundation for dynamic split inference strategies in practical edge–server deployments.
Fields of Study & Subjects
IoT and Edge/Fog Computing
Advanced Neural Network Applications
Cloud Computing and Remote Desktop Technologies
Publication details
- Journal / source
- International Conference on Consumer Electronics
- Pages
- 1–4
- Publication date
- 3 February 2026
- Language
- EN