Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search

TL;DR

This paper introduces EDNAS, a framework combining Multi-Task Learning and Neural Architecture Search to develop efficient dense prediction models for edge devices, achieving high accuracy with significantly reduced computation.

Contribution

It is the first to leverage the synergy of NAS and MTL for dense predictions, introducing JAReD to improve training stability and accuracy.

Findings

EDNAS outperforms transfer learning and prior MTL methods in accuracy.

The joint approach requires only 1/10th of the computation of single-task NAS.

JAReD reduces noise and boosts accuracy in multi-task depth training.

Abstract

In this work, we propose a novel and scalable solution to address the challenges of developing efficient dense predictions on edge platforms. Our first key insight is that MultiTask Learning (MTL) and hardware-aware Neural Architecture Search (NAS) can work in synergy to greatly benefit on-device Dense Predictions (DP). Empirical results reveal that the joint learning of the two paradigms is surprisingly effective at improving DP accuracy, achieving superior performance over both the transfer learning of single-task NAS and prior state-of-the-art approaches in MTL, all with just 1/10th of the computation. To the best of our knowledge, our framework, named EDNAS, is the first to successfully leverage the synergistic relationship of NAS and MTL for DP. Our second key insight is that the standard depth training for multi-task DP can cause significant instability and noise to MTL evaluation. Instead, we propose JAReD, an improved, easy-to-adopt Joint Absolute-Relative Depth loss, that reduces up to 88% of the undesired noise while simultaneously boosting accuracy. We conduct extensive evaluations on standard datasets, benchmark against strong baselines and state-of-the-art approaches, as well as provide an analysis of the discovered optimal architectures.