QuantNAS for super resolution: searching for efficient quantization-friendly architectures against quantization noise

by   Egor Shvetsov, et al.

There is a constant need for high-performing and computationally efficient neural network models for image super-resolution (SR) often used on low-capacity devices. One way to obtain such models is to compress existing architectures, e.g. quantization. Another option is a neural architecture search (NAS) that discovers new efficient solutions. We propose a novel quantization-aware NAS procedure for a specifically designed SR search space. Our approach performs NAS to find quantization-friendly SR models. The search relies on adding quantization noise to parameters and activations instead of quantizing parameters directly. Our QuantNAS finds architectures with better PSNR/BitOps trade-off than uniform or mixed precision quantization of fixed architectures. Additionally, our search against noise procedure is up to 30 faster than directly quantizing weights.


Journey Towards Tiny Perceptual Super-Resolution

Recent works in single-image perceptual super-resolution (SR) have demon...

Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution

This paper proposes a trilevel neural architecture search (NAS) method f...

Memory-Efficient Hierarchical Neural Architecture Search for Image Restoration

Recently, much attention has been spent on neural architecture search (N...

Towards Clip-Free Quantized Super-Resolution Networks: How to Tame Representative Images

Super-resolution (SR) networks have been investigated for a while, with ...

UDC: Unified DNAS for Compressible TinyML Models

Emerging Internet-of-things (IoT) applications are driving deployment of...

Achieving Super-Resolution with Redundant Sensing

Analog-to-digital (quantization) and digital-to-analog (de-quantization)...

Anchor-based Plain Net for Mobile Image Super-Resolution

Along with the rapid development of real-world applications, higher requ...

Please sign up or login with your details

Forgot password? Click here to reset