# Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes

arXiv: https://arxiv.org/abs/2206.08852 · HTML: https://mlsanity.com/paper/2206.08852/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 17 Jun 2022.

## Builds on (most cited first, 20 of 20)

- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [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)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks](https://mlsanity.com/paper/1807.10029/) (2018)
- [Low-bit Quantization of Neural Networks for Efficient Inference](https://mlsanity.com/paper/1902.06822/) (2019)
- [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://mlsanity.com/paper/2004.05565/) (2020)
- [MLPerf Tiny Benchmark](https://mlsanity.com/paper/2106.07597/) (2021)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [Rethinking Differentiable Search for Mixed-Precision Neural Networks](https://mlsanity.com/paper/2004.05795/) (2020)
- [DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs](https://mlsanity.com/paper/2008.07127/) (2020)
- [Fully Onboard AI-powered Human-Drone Pose Estimation on Ultra-low Power Autonomous Flying Nano-UAVs](https://mlsanity.com/paper/2103.10873/) (2021)
- [Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices](https://mlsanity.com/paper/2203.14907/) (2022)
- [A Mixed-Precision RISC-V Processor for Extreme-Edge DNN Inference](https://mlsanity.com/paper/2010.04073/) (2020)
- [Ultra-compact Binary Neural Networks for Human Activity Recognition on RISC-V Processors](https://mlsanity.com/paper/2205.12781/) (2022)

## Built on by (most cited first, 9 of 9)

- [PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimization](https://mlsanity.com/paper/2307.09488/) (2023)
- [Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications](https://mlsanity.com/paper/2508.15008/) (2025)
- [Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks](https://mlsanity.com/paper/2407.01054/) (2024)
- [MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing](https://mlsanity.com/paper/2506.02006/) (2025)
- [Precision-aware Latency and Energy Balancing on Multi-Accelerator Platforms for DNN Inference](https://mlsanity.com/paper/2306.05060/) (2023)
- [Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge](https://mlsanity.com/paper/2307.02894/) (2023)
- [Neural Precision Polarization: Simplifying Neural Network Inference with Dual-Level Precision](https://mlsanity.com/paper/2411.05845/) (2024)
- [HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays](https://mlsanity.com/paper/2402.01226/) (2024)
- [Optimizing DNN Inference on Multi-Accelerator SoCs at Training-time](https://mlsanity.com/paper/2409.18566/) (2024)

## Abstract (arXiv)

Quantization is widely employed in both cloud and edge systems to reduce the memory occupation, latency, and energy consumption of deep neural networks. In particular, mixed-precision quantization, i.e., the use of different bit-widths for different portions of the network, has been shown to provide excellent efficiency gains with limited accuracy drops, especially with optimized bit-width assignments determined by automated Neural Architecture Search (NAS) tools. State-of-the-art mixed-precision works layer-wise, i.e., it uses different bit-widths for the weights and activations tensors of each network layer. In this work, we widen the search space, proposing a novel NAS that selects the bit-width of each weight tensor channel independently. This gives the tool the additional flexibility of assigning a higher precision only to the weights associated with the most informative features. Testing on the MLPerf Tiny benchmark suite, we obtain a rich collection of Pareto-optimal models in the accuracy vs model size and accuracy vs energy spaces. When deployed on the MPIC RISC-V edge processor, our networks reduce the memory and energy for inference by up to 63% and 27% respectively compared to a layer-wise approach, for the same accuracy.