# HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays

arXiv: https://arxiv.org/abs/2402.01226 · HTML: https://mlsanity.com/paper/2402.01226/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 13 of 13)

- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://mlsanity.com/paper/2004.05565/) (2020)
- [Rethinking Differentiable Search for Mixed-Precision Neural Networks](https://mlsanity.com/paper/2004.05795/) (2020)
- [Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge](https://mlsanity.com/paper/2301.10281/) (2023)
- [Enabling Mixed-Precision Quantized Neural Networks in Extreme-Edge Devices](https://mlsanity.com/paper/2007.07759/) (2020)
- [Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes](https://mlsanity.com/paper/2206.08852/) (2022)
- [PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimization](https://mlsanity.com/paper/2307.09488/) (2023)
- [XpulpNN: Enabling Energy Efficient and Flexible Inference of Quantized Neural Network on RISC-V based IoT End Nodes](https://mlsanity.com/paper/2011.14325/) (2020)
- [Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays](https://mlsanity.com/paper/2304.06059/) (2023)

## Built on by (most cited first, 1 of 1)

- [MAUPITI: On-Device Prototype-Based Learning on a Smart Infrared Sensor](https://mlsanity.com/paper/2608.07192/) (2026)

## Abstract (arXiv)

Low-resolution infrared (IR) array sensors enable people counting applications such as monitoring the occupancy of spaces and people flows while preserving privacy and minimizing energy consumption. Deep Neural Networks (DNNs) have been shown to be well-suited to process these sensor data in an accurate and efficient manner. Nevertheless, the space of DNNs' architectures is huge and its manual exploration is burdensome and often leads to sub-optimal solutions. To overcome this problem, in this work, we propose a highly automated full-stack optimization flow for DNNs that goes from neural architecture search, mixed-precision quantization, and post-processing, down to the realization of a new smart sensor prototype, including a Microcontroller with a customized instruction set. Integrating these cross-layer optimizations, we obtain a large set of Pareto-optimal solutions in the 3D-space of energy, memory, and accuracy. Deploying such solutions on our hardware platform, we improve the state-of-the-art achieving up to 4.2x model size reduction, 23.8x code size reduction, and 15.38x energy reduction at iso-accuracy.