Deployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI

• URL: http://arxiv.org/abs/2604.24492v1
• Date: Mon, 27 Apr 2026 13:58:18 GMT
• Title: Deployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI
• Abstract summary: We introduce deployment-aligned low-precision training directly into hardware-aware neural architecture search (NAS)<n>We evaluate the proposed framework on vessel segmentation for spaceborne maritime monitoring, targeting the Intel Movidius Myriad X Visual Processing Unit (VPU)<n>Results demonstrate that incorporating deployment-consistent numerical constraints into hardware-aware NAS substantially improves robustness and alignment between optimization and deployment for resource-constrained edge Artificial Intelligence (AI)
• Score: 1.1666234644810893
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Designing deep networks that meet strict latency and accuracy constraints on edge accelerators increasingly relies on hardware-aware optimization, including neural architecture search (NAS) guided by device-level metrics. Yet most hardware-aware NAS pipelines still optimize architectures under full-precision assumptions and apply low-precision adaptation only after the search, leading to a mismatch between optimization-time behavior and deployment-time execution on low-precision hardware that can substantially degrade accuracy. We address this limitation by integrating deployment-aligned low-precision training directly into hardware-aware NAS. Candidate architectures are exposed to FP16 numerical constraints during fine-tuning and evaluation, enabling joint optimization of architectural efficiency and numerical robustness without modifying the search space or evolutionary strategy. We evaluate the proposed framework on vessel segmentation for spaceborne maritime monitoring, targeting the Intel Movidius Myriad X Visual Processing Unit (VPU). While post-training precision conversion reduces on-device performance from 0.85 to 0.78 mIoU, deployment-aligned low-precision training achieves 0.826 mIoU on-device for the same architecture (95,791 parameters), recovering approximately two-thirds of deployment-induced accuracy gap without increasing model complexity. These results demonstrate that incorporating deployment-consistent numerical constraints into hardware-aware NAS substantially improves robustness and alignment between optimization and deployment for resource-constrained edge Artificial Intelligence (AI).

Related papers

• Device-Conditioned Neural Architecture Search for Efficient Robotic Manipulation [16.017058636822025]
  We propose a unified framework named textbfDevice-textbfConditioned textbfQuantization-textbfFor-textbfAll (DC-QFA)<n>DC-QFA amortizes deployment effort with the device-conditioned quantization-aware training and hardware-constrained architecture search.
  arXiv  Detail & Related papers  (2026-04-11T11:36:16Z)
• Hardware-aware Neural Architecture Search of Early Exiting Networks on Edge Accelerators [12.394874144369396]
  Growing demand for embedded intelligence at the edge imposes stringent computational and energy constraints.<n>Early Exiting Neural Networks (EENN) have emerged as a promising solution.<n>We propose a hardware-aware Neural Architecture Search (NAS) framework to optimize the placement of early exit points within a network backbone.
  arXiv  Detail & Related papers  (2025-12-04T11:54:09Z)
• Comprehensive Design Space Exploration for Tensorized Neural Network Hardware Accelerators [11.97184801369339]
  High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment.<n>Such hardware-unaware designs often obscure the potential latency and energy benefits of tensorized models.<n>We propose a co-exploration framework that unifies these dimensions within a unified design space for efficient training and inference of tensorized neural networks.
  arXiv  Detail & Related papers  (2025-11-22T08:18:40Z)
• MaRVIn: A Cross-Layer Mixed-Precision RISC-V Framework for DNN Inference, from ISA Extension to Hardware Acceleration [4.852153649271776]
  Existing embedded microprocessors lack sufficient architectural support for efficiently executing mixed-precision NNs.<n>We introduce MaRVIn, a cross-layer hardware-software co-design framework that enhances power efficiency and performance.<n>Our framework can achieve, on average, 17.6x speedup for less than 1% accuracy loss and outperforms the ISA-agnostic state-of-the-art RISC-V cores, delivering up to 1.8 TOPs/W.
  arXiv  Detail & Related papers  (2025-09-18T17:48:20Z)
• ZeroLM: Data-Free Transformer Architecture Search for Language Models [54.83882149157548]
  Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity.<n>This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics.<n>Our evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark.
  arXiv  Detail & Related papers  (2025-03-24T13:11:22Z)
• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers [56.37495946212932]
  Vision transformers (ViTs) have demonstrated their superior accuracy for computer vision tasks compared to convolutional neural networks (CNNs) This work proposes Quasar-ViT, a hardware-oriented quantization-aware architecture search framework for ViTs.
  arXiv  Detail & Related papers  (2024-07-25T16:35:46Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Multi-Exit Semantic Segmentation Networks [78.44441236864057]
  We propose a framework for converting state-of-the-art segmentation models to MESS networks. specially trained CNNs that employ parametrised early exits along their depth to save during inference on easier samples. We co-optimise the number, placement and architecture of the attached segmentation heads, along with the exit policy, to adapt to the device capabilities and application-specific requirements.
  arXiv  Detail & Related papers  (2021-06-07T11:37:03Z)
• Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs [13.628734116014819]
  Deep learning on embedded devices has prompted the development of numerous methods to optimise the deployment of deep neural networks (DNN) There is a lack of research on cross-level optimisation as the space of approaches becomes too large to test and obtain a globally optimised solution. We present a set of results for state-of-the-art DNNs on a range of Arm Cortex-A CPU platforms achieving up to 4x improvement in performance and over 2x reduction in memory.
  arXiv  Detail & Related papers  (2020-06-09T11:00:06Z)
• PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning [57.20262984116752]
  We introduce a new dimension, fine-grained pruning patterns inside the coarse-grained structures, revealing a previously unknown point in design space. With the higher accuracy enabled by fine-grained pruning patterns, the unique insight is to use the compiler to re-gain and guarantee high hardware efficiency.
  arXiv  Detail & Related papers  (2020-01-01T04:52:07Z)

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.