An affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platforms

• URL: http://arxiv.org/abs/2606.16290v1
• Date: Mon, 15 Jun 2026 06:51:53 GMT
• Title: An affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platforms
• Abstract summary: Hardware-aware neural architecture search (HW-NAS) allows the integration of Convolutional Neural Networks (CNNs) in microcontrollers devices.<n>This work presents a HW-NAS generating tiny CNNs that can run on ultra-low-power microcontrollers.
• Score: 3.1945067016153437
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hardware-aware neural architecture search (HW-NAS) allows the integration of Convolutional Neural Networks (CNNs) in microcontrollers devices by automatically designing neural architectures that can fit prearranged hardware constraints. However, state-of-the-art HW-NAS target high-performance microcontrollers, whose power consumption does not meet sensing nodes requirements. This work presents a HW-NAS generating tiny CNNs that can run on ultra-low-power microcontrollers, featuring a lightweight search procedure enabling its execution even on embedded devices. Empirical results on three well-known benchmarks for tiny computer vision proved that the proposed HW-NAS was able to generate tiny CNNs while preserving state-of-the-art classification accuracy.

Related papers

• Running hardware-aware neural architecture search on embedded devices under 512MB of RAM [3.194506701615343]
  The presented HW NAS produces tiny convolutional neural networks (CNNs) targeting low-end microcontroller units (MCUs)<n>A gateway could run it to tailor CNNs' architecture on the acquired data without using external servers, ensuring privacy.<n>The technique achieves state-of-the-art results in the human-recognition tasks on the Visual Wake Word dataset, a standard TinyML benchmark, on several embedded devices.
  arXiv  Detail & Related papers  (2026-06-12T13:28:49Z)
• ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures [60.14199724905456]
  ONNX-Bench is a benchmark consisting of a collection of neural networks in a unified format based on ONNX files.<n> ONNX-Net represents any neural architecture using natural language descriptions acting as an input to a performance predictor.<n>Experiments show strong zero-shot performance across disparate search spaces using only a small amount of pretraining samples.
  arXiv  Detail & Related papers  (2025-10-06T15:43:36Z)
• DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions [121.05720140641189]
  We develop a family of models with the distilling neural architecture (DNA) techniques. Our proposed DNA models can rate all architecture candidates, as opposed to previous works that can only access a sub- search space using algorithms. Our models achieve state-of-the-art top-1 accuracy of 78.9% and 83.6% on ImageNet for a mobile convolutional network and a small vision transformer, respectively.
  arXiv  Detail & Related papers  (2024-03-02T22:16:47Z)
• Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones [9.806742394395322]
  Miniaturized unmanned aerial vehicles (UAVs) are gaining popularity due to their small size, enabling new tasks such as indoor navigation or people monitoring. This work proposes a new automatic optimization pipeline for visual pose estimation tasks using Deep Neural Networks (DNNs) Our results improve the state-of-the-art reducing inference latency by up to 3.22x at iso-error.
  arXiv  Detail & Related papers  (2024-02-23T11:35:57Z)
• SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems [6.006032394972252]
  Spiking Neural Networks (SNNs) offer high accuracy and ultra low-power/energy computation.<n>SpikeNAS is a novel fast memory-aware neural architecture search framework for SNNs.<n>Our results show that our SpikeNAS improves the searching time and maintains high accuracy compared to state-of-the-art.
  arXiv  Detail & Related papers  (2024-02-17T16:33:54Z)
• Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs [69.19616451596342]
  Miniaturized unmanned aerial vehicles (UAVs) are an emerging and trending topic. We leverage a novel neural architecture search (NAS) technique to automatically identify several convolutional neural networks (CNNs) for a visual pose estimation task. Our results improve the State-of-the-Art by reducing the in-field control error of 32% while achieving a real-time onboard inference-rate of 10Hz@10mW and 50Hz@90mW.
  arXiv  Detail & Related papers  (2023-03-03T14:02:09Z)
• Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor [1.6309682969263486]
  ColabNAS is an affordable hardware-aware neural architecture search (HW NAS) technique for producing task-specific CNNs. Its novel derivative-free search strategy, inspired by Occam's razor, allows to obtain state-of-the-art results on the Visual Wake Word dataset.
  arXiv  Detail & Related papers  (2022-12-15T10:23:32Z)
• FPGA-optimized Hardware acceleration for Spiking Neural Networks [69.49429223251178]
  This work presents the development of a hardware accelerator for an SNN, with off-line training, applied to an image recognition task. The design targets a Xilinx Artix-7 FPGA, using in total around the 40% of the available hardware resources. It reduces the classification time by three orders of magnitude, with a small 4.5% impact on the accuracy, if compared to its software, full precision counterpart.
  arXiv  Detail & Related papers  (2022-01-18T13:59:22Z)
• Neural Architecture Search of SPD Manifold Networks [79.45110063435617]
  We propose a new neural architecture search (NAS) problem of Symmetric Positive Definite (SPD) manifold networks. We first introduce a geometrically rich and diverse SPD neural architecture search space for an efficient SPD cell design. We exploit a differentiable NAS algorithm on our relaxed continuous search space for SPD neural architecture search.
  arXiv  Detail & Related papers  (2020-10-27T18:08:57Z)
• MS-RANAS: Multi-Scale Resource-Aware Neural Architecture Search [94.80212602202518]
  We propose Multi-Scale Resource-Aware Neural Architecture Search (MS-RANAS) We employ a one-shot architecture search approach in order to obtain a reduced search cost. We achieve state-of-the-art results in terms of accuracy-speed trade-off.
  arXiv  Detail & Related papers  (2020-09-29T11:56:01Z)
• S3NAS: Fast NPU-aware Neural Architecture Search Methodology [2.607400740040335]
  We present a fast NPU-aware NAS methodology, called S3NAS, to find a CNN architecture with higher accuracy than the existing ones. We are able to find a network in 3 hours using TPUv3, which shows 82.72% top-1 accuracy on ImageNet with 11.66 ms latency.
  arXiv  Detail & Related papers  (2020-09-04T04:45:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.