Neural Architecture Search (NAS) has become the de-facto approach for designing accurate and efficient networks for edge devices. Since models are typically quantized for edge deployment, recent work has investigated quantization-aware NAS (QA-NAS) to search for highly accurate and efficient quantized models. However, existing QA-NAS approaches, particularly few-bit mixed-precision (FB-MP) methods, do not scale to larger tasks. Consequently, QA-NAS has mostly been limited to low-scale tasks and tiny networks. In this work, we present an approach to enable QA-NAS (INT8 and FB-MP) on large-scale tasks by leveraging the block-wise formulation introduced by block-wise NAS. We demonstrate strong results for the semantic segmentation task on the Cityscapes dataset, finding FB-MP models 33% smaller and INT8 models 17.6% faster than DeepLabV3 (INT8) without compromising task performance.
@article{arxiv.2401.12350,
title = {Scaling Up Quantization-Aware Neural Architecture Search for Efficient Deep Learning on the Edge},
author = {Yao Lu and Hiram Rayo Torres Rodriguez and Sebastian Vogel and Nick van de Waterlaat and Pavol Jancura},
journal= {arXiv preprint arXiv:2401.12350},
year = {2024}
}
Comments
Accepted at Workshop on Compilers, Deployment, and Tooling for Edge AI (CODAI '23 ), September 21, 2023, Hamburg, Germany