# PhiNets: a scalable backbone for low-power AI at the edge

arXiv: https://arxiv.org/abs/2110.00337 · HTML: https://mlsanity.com/paper/2110.00337/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 45 references that are in the map.
- First posted on arXiv 1 Oct 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking](https://mlsanity.com/paper/2004.01888/) (2020)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking](https://mlsanity.com/paper/1504.01942/) (2015)
- [CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs](https://mlsanity.com/paper/1801.06601/) (2018)
- [Convergence of Edge Computing and Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/1907.08349/) (2019)
- [XNOR-Net++: Improved Binary Neural Networks](https://mlsanity.com/paper/1909.13863/) (2019)
- [ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation](https://mlsanity.com/paper/1812.08934/) (2018)
- [PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V Processors](https://mlsanity.com/paper/1908.11263/) (2019)
- [Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design](https://mlsanity.com/paper/2103.15750/) (2021)
- [SCANN: Synthesis of Compact and Accurate Neural Networks](https://mlsanity.com/paper/1904.09090/) (2019)
- [Memory-efficient Speech Recognition on Smart Devices](https://mlsanity.com/paper/2102.11531/) (2021)
- [Memory-Efficient, Limb Position-Aware Hand Gesture Recognition using Hyperdimensional Computing](https://mlsanity.com/paper/2103.05267/) (2021)
- [TUTOR: Training Neural Networks Using Decision Rules as Model Priors](https://mlsanity.com/paper/2010.05429/) (2020)
- [A 1D-CNN Based Deep Learning Technique for Sleep Apnea Detection in IoT Sensors](https://mlsanity.com/paper/2105.00528/) (2021)

## Built on by (most cited first, 16 of 16)

- [Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models](https://mlsanity.com/paper/2503.06027/) (2025)
- [PaSTe: Improving the Efficiency of Visual Anomaly Detection at the Edge](https://mlsanity.com/paper/2410.11591/) (2024)
- [TinyML: Tools, Applications, Challenges, and Future Research Directions](https://mlsanity.com/paper/2303.13569/) (2023)
- [Latent Distillation for Continual Object Detection at the Edge](https://mlsanity.com/paper/2409.01872/) (2024)
- [DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units](https://mlsanity.com/paper/2410.16769/) (2024)
- [Software Engineering Approaches for TinyML based IoT Embedded Vision: A Systematic Literature Review](https://mlsanity.com/paper/2204.08702/) (2022)
- [tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models](https://mlsanity.com/paper/2311.14517/) (2023)
- [EHWGesture -- A dataset for multimodal understanding of clinical gestures](https://mlsanity.com/paper/2509.07525/) (2025)
- [Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients](https://mlsanity.com/paper/2405.17376/) (2024)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutions](https://mlsanity.com/paper/2604.06435/) (2026)
- [Scaling strategies for on-device low-complexity source separation with Conv-Tasnet](https://mlsanity.com/paper/2303.03005/) (2023)
- [Explicit modelling of subject dependency in BCI decoding](https://mlsanity.com/paper/2509.23247/) (2025)
- [Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones](https://mlsanity.com/paper/2603.26551/) (2026)
- [Elastic Spiking Transformers for Efficient Gesture Understanding](https://mlsanity.com/paper/2605.13869/) (2026)
- [GaLe: memory-efficient Global Approximate and Local Exact features](https://mlsanity.com/paper/2609.02689/) (2026)

## Abstract (arXiv)

In the Internet of Things era, where we see many interconnected and heterogeneous mobile and fixed smart devices, distributing the intelligence from the cloud to the edge has become a necessity. Due to limited computational and communication capabilities, low memory and limited energy budget, bringing artificial intelligence algorithms to peripheral devices, such as the end-nodes of a sensor network, is a challenging task and requires the design of innovative methods. In this work, we present PhiNets, a new scalable backbone optimized for deep-learning-based image processing on resource-constrained platforms. PhiNets are based on inverted residual blocks specifically designed to decouple the computational cost, working memory, and parameter memory, thus exploiting all the available resources. With a YoloV2 detection head and Simple Online and Realtime Tracking, the proposed architecture has achieved the state-of-the-art results in (i) detection on the COCO and VOC2012 benchmarks, and (ii) tracking on the MOT15 benchmark. PhiNets reduce the parameter count of 87% to 93% with respect to previous state-of-the-art models (EfficientNetv1, MobileNetv2) and achieve better performance with lower computational cost. Moreover, we demonstrate our approach on a prototype node based on a STM32H743 microcontroller (MCU) with 2MB of internal Flash and 1MB of RAM and achieve power requirements in the order of 10 mW. The code for the PhiNets is publicly available on GitHub.