Anchor-based Plain Net for Mobile Image Super-Resolution

TL;DR

This paper introduces Anchor-based Plain Net (ABPN), an efficient mobile-friendly image super-resolution architecture optimized for 8-bit quantization, achieving significant performance improvements over existing quantized models.

Contribution

The paper proposes a novel architecture, ABPN, optimized for 8-bit quantization on mobile devices, and demonstrates its superior performance through quantization-aware training.

Findings

ABPN outperforms 8-bit quantized FSRCNN by nearly 2dB PSNR.

Meta-node latency analysis guides architecture design for mobile deployment.

Quantization-aware training enhances model performance on mobile hardware.

Abstract

Along with the rapid development of real-world applications, higher requirements on the accuracy and efficiency of image super-resolution (SR) are brought forward. Though existing methods have achieved remarkable success, the majority of them demand plenty of computational resources and large amount of RAM, and thus they can not be well applied to mobile device. In this paper, we aim at designing efficient architecture for 8-bit quantization and deploy it on mobile device. First, we conduct an experiment about meta-node latency by decomposing lightweight SR architectures, which determines the portable operations we can utilize. Then, we dig deeper into what kind of architecture is beneficial to 8-bit quantization and propose anchor-based plain net (ABPN). Finally, we adopt quantization-aware training strategy to further boost the performance. Our model can outperform 8-bit quantized FSRCNN by nearly 2dB in terms of PSNR, while satisfying realistic needs at the same time. Code is avaliable at https://github.com/NJU- Jet/SR_Mobile_Quantization.