# SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems

arXiv: https://arxiv.org/abs/2204.04705 · HTML: https://mlsanity.com/paper/2204.04705/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 66 references that are in the map.
- First posted on arXiv 10 Apr 2022.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models](https://mlsanity.com/paper/2003.11142/) (2020)
- [Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks](https://mlsanity.com/paper/1909.13144/) (2019)
- [Training with Quantization Noise for Extreme Model Compression](https://mlsanity.com/paper/2004.07320/) (2020)
- [HAT: Hardware-Aware Transformers for Efficient Natural Language Processing](https://mlsanity.com/paper/2005.14187/) (2020)
- [FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search](https://mlsanity.com/paper/1907.01845/) (2019)
- [Genetic CNN](https://mlsanity.com/paper/1703.01513/) (2017)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems](https://mlsanity.com/paper/1910.14315/) (2019)
- [JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services](https://mlsanity.com/paper/1801.08618/) (2018)

## Built on by (most cited first, 14 of 14)

- [Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information](https://mlsanity.com/paper/2305.04146/) (2023)
- [Marsellus: A Heterogeneous RISC-V AI-IoT End-Node SoC with 2-to-8b DNN Acceleration and 30%-Boost Adaptive Body Biasing](https://mlsanity.com/paper/2305.08415/) (2023)
- [PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors](https://mlsanity.com/paper/2304.05440/) (2023)
- [Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction](https://mlsanity.com/paper/2412.10448/) (2024)
- [Measuring and Controlling Split Layer Privacy Leakage Using Fisher Information](https://mlsanity.com/paper/2209.10119/) (2022)
- [Slimmable Encoders for Flexible Split DNNs in Bandwidth and Resource Constrained IoT Systems](https://mlsanity.com/paper/2306.12691/) (2023)
- [Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing](https://mlsanity.com/paper/2310.13384/) (2023)
- [DISCO: Distributed Inference with Sparse Communications](https://mlsanity.com/paper/2302.11180/) (2023)
- [Edge-Only Universal Adversarial Attacks in Distributed Learning](https://mlsanity.com/paper/2411.10500/) (2024)
- [Neural Architecture Search of Hybrid Models for NPU-CIM Heterogeneous AR/VR Devices](https://mlsanity.com/paper/2410.08326/) (2024)
- [Fault-Tolerant Collaborative Inference through the Edge-PRUNE Framework](https://mlsanity.com/paper/2206.08152/) (2022)
- [DeepEOSNet: Capturing the dependency on thermodynamic state in property prediction tasks](https://mlsanity.com/paper/2509.17018/) (2025)
- [Spectrum-Aware Bounds on Invertibility for Privacy-Enhancing Instance Encoding](https://mlsanity.com/paper/2608.23382/) (2026)
- [EV-JEPA: Elastic V-JEPA for Any Device and Cross-Device Inference](https://mlsanity.com/paper/2610.14324/) (2026)

## Abstract (arXiv)

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.