MS-RANAS: Multi-Scale Resource-Aware Neural Architecture Search

TL;DR

This paper introduces MS-RANAS, a neural architecture search method that optimizes neural networks for image classification under strict computational constraints, balancing accuracy, speed, and memory.

Contribution

It proposes a multi-scale, resource-aware NAS approach using one-shot search and early classifiers for efficient, high-performance neural networks.

Findings

Achieved state-of-the-art accuracy-speed trade-offs.

Reduced search cost with one-shot architecture search.

Effective in low-memory, low-power deployment scenarios.

Abstract

Neural Architecture Search (NAS) has proved effective in offering outperforming alternatives to handcrafted neural networks. In this paper we analyse the benefits of NAS for image classification tasks under strict computational constraints. Our aim is to automate the design of highly efficient deep neural networks, capable of offering fast and accurate predictions and that could be deployed on a low-memory, low-power system-on-chip. The task thus becomes a three-party trade-off between accuracy, computational complexity, and memory requirements. To address this concern, 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 and we focus on an anytime prediction setting. Through the usage of multiple-scaled features and early classifiers, we achieved state-of-the-art results in terms of accuracy-speed trade-off.