SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems
This work addresses the challenge of deploying neural networks on resource-constrained head-mounted devices, which is incremental as it builds on existing neural architecture search methods for distributed systems.
The authors tackled the problem of designing deep neural networks for efficient distributed computing on head-mounted systems by introducing SplitNets, a split-aware neural architecture search framework that balances computation, communication, and performance, achieving state-of-the-art accuracy and latency on ImageNet and 3D classification tasks.
We design deep neural networks (DNNs) and corresponding networks' splittings to distribute DNNs' workload to camera sensors and a centralized aggregator on head mounted devices to meet system performance targets in inference accuracy and latency under the given hardware resource constraints. To achieve an optimal balance among computation, communication, and performance, a split-aware neural architecture search framework, SplitNets, is introduced to conduct model designing, splitting, and communication reduction simultaneously. We further extend the framework to multi-view systems for learning to fuse inputs from multiple camera sensors with optimal performance and systemic efficiency. We validate SplitNets for single-view system on ImageNet as well as multi-view system on 3D classification, and show that the SplitNets framework achieves state-of-the-art (SOTA) performance and system latency compared with existing approaches.