No-reference image quality assessment with multi-scale weighted residuals and channel attention mechanism

Wang, Changzhong; Lv, Xiang; Ding, Weiping; Fan, Xiaodong

doi:10.1007/s00500-022-07535-5

Cited by 4 publications

(2 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With respect to the design of network structure, we adopt different network structures for different datasets. In our experiments, we found that it is not true that the more complex the model structure, the higher the quality of the generated adversarial examples [56,57] . Based on this principle, the network structures we designed for the three datasets, MNIST, Fashion-MNIST, and CIFAR10, are given in Table 1.…”

Section: Network Structure Design For Three Datasetsmentioning

confidence: 79%

DCVAE-adv: A Universal Adversarial Example Generation Method for White and Black Box Attacks

Xu,

Zhai

2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

Deep neural network (DNN) has strong representation learning ability, but it is vulnerable and easy to be fooled by adversarial examples. In order to handle the vulnerability of DNN, many methods have been proposed.The general idea of existing methods is to reduce the chance of DNN models being fooled by observing some designed adversarial examples, which are generated by adding perturbations to the original images. In this paper, we propose a novel adversarial example generation method, called DCVAE-adv. Different from the existing methods, DCVAE-adv constructs adversarial examples by mixing both explicit and implicit perturbations without using original images. Furthermore, the proposed method can be applied to both white box and black box attacks. In addition, in the inference stage, the adversarial examples can be generated without loading the original images into memory, which greatly reduces the memory overhead. We compared DCVAE-adv with three most advanced adversarial attack algorithms: FGSM, AdvGAN, and AdvGAN++. The experimental results demonstrate that DCVAE-adv is superior to these state-of-the-art methods in terms of attack success rate and transfer ability for targeted attack. Our code is available at https://github.com/xzforeverlove/DCVAE-adv.

show abstract

Section: Network Structure Design For Three Datasetsmentioning

confidence: 79%

DCVAE-adv: A Universal Adversarial Example Generation Method for White and Black Box Attacks

Xu,

Zhai

2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Following refs. [15,27,35,36], our training strategy involves non-overlapping cropping of images input into the network into blocks of size 32 × 32. The quality scores for each image block were inherited from the original image.…”

Section: Implementation Detailsmentioning

confidence: 99%

No‐reference image quality assessment via a dual‐branch residual network

Ji,

Liu,

Chen

2024

IET Image Processing

View full text Add to dashboard Cite

The No‐Reference Image Quality Assessment (NR‐IQA) method can predict quality scores of distorted images without the reference image. However, due to the variability in both color and structure of images, existing NR‐IQA methods struggle to accurately predict quality scores of distorted images. Therefore, an NR‐IQA method based on a Dual‐Branch Residual Network (DBRIQA) for evaluating the quality scores of color‐distorted images is proposed. First, guided filtering is applied to the hue images in the HSV space to extract distortion information from the image's color. Then, due to significant differences in distorted images, enhancements are made to the traditional residual blocks, forming a feature extraction module that captures multi‐scale features from the image. In order to capture the global relationships in the distorted image, a Global‐Level Attention Block (GLAB) is introduced, facilitating the interaction of information among the extracted features. Experiments were conducted across four publicly available IQA datasets, including LIVE, CSIQ, TID2008, and TID2013. The experimental results demonstrate that the proposed method exhibits strong performance and generalization capabilities in predicting image quality compared to peer methods.

show abstract

Image super-resolution with multi-scale fractal residual attention network

Song

Liu

et al. 2023

Computers & Graphics

View full text Add to dashboard Cite

No-reference image quality assessment with multi-scale weighted residuals and channel attention mechanism

Cited by 4 publications

References 58 publications

DCVAE-adv: A Universal Adversarial Example Generation Method for White and Black Box Attacks

DCVAE-adv: A Universal Adversarial Example Generation Method for White and Black Box Attacks

No‐reference image quality assessment via a dual‐branch residual network

Image super-resolution with multi-scale fractal residual attention network

Contact Info

Product

Resources

About