Channel Attention for No-Reference Image Quality Assessment in DCT Domain

Attention mechanism, especially self-attention, has gained great success in image quality assessment. The advent of Transformer has led to a substantial enhancement in no-reference image quality assessment (NR-IQA). Existing works focus on leveraging the global perceptual capability of Transformer e...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2024, Vol.31, p.1274-1278
Main Authors: Wang, Zesheng, Yuan, Liang, Zhai, Guangtao
Format: Article
Language:English
Subjects:
Channel attention
Channels
Coders
Discrete cosine transform
Discrete cosine transforms
Distortion
Feature decomposition
Feature extraction
Image enhancement
Image quality
image quality assessment
Quality assessment
Task analysis
Training
transformer
Transformers
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Attention mechanism, especially self-attention, has gained great success in image quality assessment. The advent of Transformer has led to a substantial enhancement in no-reference image quality assessment (NR-IQA). Existing works focus on leveraging the global perceptual capability of Transformer encoders to perceive image quality. In this work, we start from a different view and propose a novel multi-frequency channel attention framework for Transformer encoder. Through frequency analysis, we demonstrate mathematically that traditional global average pooling (GAP) is a specific instance of feature decomposition in the frequency domain. With the proof, we use the discrete cosine transform to compress channels, which optimally compresses channels by efficiently utilizing frequency components overlooked by GAP. The experimental results show that the proposed method leads to improvements of performance over the state-of-the-art methods.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2024.3392671