ASCAM-Former: Blind image quality assessment based on adaptive spatial &amp; channel attention merging transformer and image to patch weights sharing

Ma, Xiaoyu; Zhang, Suiyu; Wang, Yaqi; Li, Rong; Chen, Xiaodiao; Yu, Dingguo

doi:10.1016/j.eswa.2022.119268

Search citation statements

Order By: Relevance

Paper Sections

Select...

The Proposed Resnet14attention1

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Article7

Relationship

Self Cite0

Independent7

Authors

Journals

Cited by 11 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the efficiency and accuracy of visual information processing are highly improved by the guidance of attention mechanism weights. In different situations, the attention mechanism can determine different important information by adjusting the weights to satisfy the requirements of different focus objects [ 49 ].…”

Section: The Proposed Resnet14attentionmentioning

confidence: 99%

ResNet14Attention network for identifying the titration end-point of potassium dichromate

Liang

Yin

Zhang

et al. 2023

Heliyon

View full text Add to dashboard Cite

Section: The Proposed Resnet14attentionmentioning

confidence: 99%

ResNet14Attention network for identifying the titration end-point of potassium dichromate

Liang

Yin

Zhang

et al. 2023

Heliyon

View full text Add to dashboard Cite

“…Over the last decade, various IQA methods have been proposed and achieved impressive performance. For instance, Ma et al [9] proposed the ASCAM-Former that introduces the channel-wised self-attention into IQA. The spatial and channel dependencies among features are characterized, rendering to a comprehensive quality evaluation.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Underwater Image Quality Assessment with Influential Perceptual Features

Liu,

Huang,

Xie

et al. 2023

Electronics

View full text Add to dashboard Cite

In the multifaceted field of oceanic engineering, the quality of underwater images is paramount for a range of applications, from marine biology to robotic exploration. This paper presents a novel approach in underwater image quality assessment (UIQA) that addresses the current limitations by effectively combining low-level image properties with high-level semantic features. Traditional UIQA methods predominantly focus on either low-level attributes such as brightness and contrast or high-level semantic content, but rarely both, which leads to a gap in achieving a comprehensive assessment of image quality. Our proposed methodology bridges this gap by integrating these two critical aspects of underwater imaging. We employ the least-angle regression technique for balanced feature selection, particularly in high-level semantics, to ensure that the extensive feature dimensions of high-level content do not overshadow the fundamental low-level properties. The experimental results of our method demonstrate a remarkable improvement over existing UIQA techniques, establishing a new benchmark in both accuracy and reliability for underwater image assessment.

show abstract

OmiQnet: Multiscale feature aggregation convolutional neural network for omnidirectional image assessment

Fan,

Chen

2024

Appl Intell

View full text Add to dashboard Cite

ASCAM-Former: Blind image quality assessment based on adaptive spatial & channel attention merging transformer and image to patch weights sharing

Cited by 11 publications

References 34 publications

ResNet14Attention network for identifying the titration end-point of potassium dichromate

ResNet14Attention network for identifying the titration end-point of potassium dichromate

Enhancing Underwater Image Quality Assessment with Influential Perceptual Features

OmiQnet: Multiscale feature aggregation convolutional neural network for omnidirectional image assessment

Contact Info

Product

Resources

About