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

arXiv: https://arxiv.org/abs/2604.24492 · HTML: https://mlsanity.com/paper/2604.24492/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [ZeroQ: A Novel Zero Shot Quantization Framework](https://mlsanity.com/paper/2001.00281/) (2020)
- [Low-bit Quantization of Neural Networks for Efficient Inference](https://mlsanity.com/paper/1902.06822/) (2019)
- [NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search](https://mlsanity.com/paper/2001.10422/) (2020)
- [DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures](https://mlsanity.com/paper/1806.08198/) (2018)
- [Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward](https://mlsanity.com/paper/2305.08413/) (2023)
- [On Board Volcanic Eruption Detection through CNNs and Satellite Multispectral Imagery](https://mlsanity.com/paper/2106.15281/) (2021)
- [Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture Search](https://mlsanity.com/paper/2410.05425/) (2024)
- [Assessing the Added Value of Onboard Earth Observation Processing with the IRIDE HEO Service Segment](https://mlsanity.com/paper/2604.07120/) (2026)

## Abstract (arXiv)

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).