Loading...

(ASNA) an attention-based Siamese-difference neural network with surrogate ranking loss function for perceptual image quality assessment

Ayyoubzadeh, M ; Sharif University of Technology | 2021

1442 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/CVPRW53098.2021.00049
  3. Publisher: IEEE Computer Society , 2021
  4. Abstract:
  5. Recently, deep convolutional neural networks (DCNN) that leverage the adversarial training framework for image restoration and enhancement have significantly improved the processed images' sharpness. Surprisingly, although these DCNNs produced crispier images than other methods visually, they may get a lower quality score when popular measures are employed for evaluating them. Therefore it is necessary to develop a quantitative metric to reflect their performances, which is well-aligned with the perceived quality of an image. Famous quantitative metrics such as Peak signal-to-noise ratio (PSNR), The structural similarity index measure (SSIM), and Perceptual Index (PI) are not well-correlated with the mean opinion score (MOS) for an image, especially for the neural networks trained with adversarial loss functions. This paper has proposed a convolutional neural network using an extension architecture of the traditional Siamese network so-called Siamese-Difference neural network. We have equipped this architecture with the spatial and channel-wise attention mechanism to increase our method's performance. Finally, we employed an auxiliary loss function to train our model. The suggested additional cost function surrogates ranking loss to increase Spearman's rank correlation coefficient while it is differentiable concerning the neural network parameters. Our method achieved superior performance in NTIRE 2021 Perceptual Image Quality Assessment Challenge. The implementations of our proposed method are publicly available.1 2 © 2021 IEEE
  6. Keywords:
  7. Convolution ; Convolutional neural networks ; Cost functions ; Image enhancement ; Image quality ; Image reconstruction ; Network architecture ; Signal to noise ratio ; Image quality assessment ; Image restoration and enhancements ; Image sharpness ; Loss functions ; Neural-networks ; Perceptual image quality ; Performance ; Processed images ; Quantitative metric ; Training framework ; Deep neural networks
  8. Source: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021, 19 June 2021 through 25 June 2021 ; 2021 , Pages 388-397 ; 21607508 (ISSN); 9781665448994 (ISBN)
  9. URL: https://ieeexplore.ieee.org/document/9523183