MSANet: multi-scale attention guided deep neural network for blind image quality assessment

Xiaoyu Ma; Jiaojiao Wang

doi:10.1117/12.2624147

19 December 2021 MSANet: multi-scale attention guided deep neural network for blind image quality assessment

Xiaoyu Ma, Jiaojiao Wang

Proceedings Volume 12128, Second International Conference on Industrial IoT, Big Data, and Supply Chain; 121280Z (2021) https://doi.org/10.1117/12.2624147
Event: 2nd International Conference on Industrial IoT, Big Data, and Supply Chain, 2021, Macao, China

Abstract

This work explores how to efficiently incorporate both the multi-scale features and attention mechanism into blind image quality assessment modules and proposes an end-to-end multi-scale attention guided deep neural network for perceptual quality assessment. Our method is established on a hierarchical learning framework in which two learning stages including coarse learning upon single-scale and quality refinement upon multi-scale, by which the quality-aware features could effectively extracted and aggregated into quality prediction scores. The proposed MSANet is based on the observation that multi-scale features could provide more flexible and robust features for BIQA whilst attention mechanism are beneficial for quality-aware feature aggregating. Through performance comparison with the state-of-theart approaches, our proposed mothed shows promising potential for blindly measuring the perceptual quality of distorted images.

Citation Download Citation

Xiaoyu Ma and Jiaojiao Wang "MSANet: multi-scale attention guided deep neural network for blind image quality assessment", Proc. SPIE 12128, Second International Conference on Industrial IoT, Big Data, and Supply Chain, 121280Z (19 December 2021); https://doi.org/10.1117/12.2624147

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image quality

Feature extraction

Neural networks

Databases

Digital imaging

Distortion

Visual system

Show All Keywords

Keywords/Phrases

Search In:

Publication Years