mlsanityData to 7 Oct 2026

Conformer and Blind Noisy Students for Improved Image Quality Assessment

arXiv 2204.12819 ↗First posted 27 Apr 2022eess.IV cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Generative models for image restoration, enhancement, and generation have significantly improved the quality of the generated images. Surprisingly, these models produce more pleasant images to the human eye than other methods, yet, they may get a lower perceptual quality score using traditional perceptual quality metrics such as PSNR or SSIM. Therefore, it is necessary to develop a quantitative metric to reflect the performance of new algorithms, which should be well-aligned with the person's mean opinion score (MOS). Learning-based approaches for perceptual image quality assessment (IQA) usually require both the distorted and reference image for measuring the perceptual quality accurately. However, commonly only the distorted or generated image is available. In this work, we explore the performance of transformer-based full-reference IQA models. We also propose a method for IQA based on semi-supervised knowledge distillation from full-reference teacher models into blind student models using noisy pseudo-labeled data. Our approaches achieved competitive results on the NTIRE 2022 Perceptual Image Quality Assessment Challenge: our full-reference model was ranked 4th, and our blind noisy student was ranked 3rd among 70 participants, each in their respective track.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 36 of its 70 references that are in the map. First posted on arXiv 27 Apr 2022.

Builds on

36 of 70 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2022A ConvNet for the 2020scited by 3,545
  7. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  8. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  9. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  11. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  12. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
24 more
  1. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  2. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  3. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  4. 2017The Perception-Distortion Tradeoffcited by 582
  5. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 351
  6. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 224
  7. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  8. 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 193
  9. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 177
  10. 2018PieAPP: Perceptual Image-Error Assessment through Pairwise Preferencecited by 158
  11. 2018The 2018 PIRM Challenge on Perceptual Image Super-resolutioncited by 155
  12. 2016Learning a No-Reference Quality Metric for Single-Image Super-Resolutioncited by 143
  13. 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
  14. 2021Perceptual Image Quality Assessment with Transformerscited by 54
  15. 2015Seven ways to improve example-based single image super resolutioncited by 51
  16. 2021NTIRE 2021 Challenge on Image Deblurringcited by 49
  17. 2021Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognitioncited by 42
  18. 2020Image Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and Metriccited by 26
  19. 2021NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Resultscited by 26
  20. 2021NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Resultscited by 22
  21. 2021NTIRE 2021 Challenge on Perceptual Image Quality Assessmentcited by 18
  22. 2021Region-Adaptive Deformable Network for Image Quality Assessmentcited by 14
  23. 2018Generative adversarial network-based image super-resolution using perceptual content lossescited by 8
  24. 2021(ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss function for Perceptual Image Quality Assessmentcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 1.

5 papers.

  1. 2022Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restorationcited by 72
  2. 2022NTIRE 2022 Challenge on Perceptual Image Quality Assessmentcited by 41
  3. 2022Perceptual Image Enhancement for Smartphone Real-Time Applicationscited by 18
  4. 2022Real-Time Under-Display Cameras Image Restoration and HDR on Mobile Devicescited by 5
  5. 2023Blind CT Image Quality Assessment Using DDPM-derived Content and Transformer-based Evaluatorcited by 1