mlsanityData to 7 Oct 2026

Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment

arXiv 2404.19567 ↗First posted 30 Apr 2024cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Despite great success in modeling visual perception, deep neural network based image quality assessment (IQA) still remains unreliable in real-world applications due to its vulnerability to adversarial perturbations and the inexplicit black-box structure. In this paper, we propose to build a trustworthy IQA model via Causal Perception inspired Representation Learning (CPRL), and a score reflection attack method for IQA model. More specifically, we assume that each image is composed of Causal Perception Representation (CPR) and non-causal perception representation (N-CPR). CPR serves as the causation of the subjective quality label, which is invariant to the imperceptible adversarial perturbations. Inversely, N-CPR presents spurious associations with the subjective quality label, which may significantly change with the adversarial perturbations. To extract the CPR from each input image, we develop a soft ranking based channel-wise activation function to mediate the causally sufficient (beneficial for high prediction accuracy) and necessary (beneficial for high robustness) deep features, and based on intervention employ minimax game to optimize. Experiments on four benchmark databases show that the proposed CPRL method outperforms many state-of-the-art adversarial defense methods and provides explicit model interpretation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 30 Apr 2024.

Builds on

36 of 58 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  5. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  6. 2018Robustness May Be at Odds with Accuracycited by 873
  7. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  8. 2017NIMA: Neural Image Assessmentcited by 387
  9. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  10. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 301
  11. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  12. 2018Adversarial Logit Pairingcited by 224
24 more
  1. 2015Massive Online Crowdsourced Study of Subjective and Objective Picture Qualitycited by 208
  2. 2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
  3. 2019Adversarial Robustness through Local Linearizationcited by 146
  4. 2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
  5. 2020Feature Purification: How Adversarial Training Performs Robust Deep Learningcited by 107
  6. 2022Causal Machine Learning: A Survey and Open Problemscited by 107
  7. 2013Probabilities of Causation: Bounds and Identificationcited by 89
  8. 2020Smooth Adversarial Trainingcited by 89
  9. 2020Transformer for Image Quality Assessmentcited by 76
  10. 2021Desiderata for Representation Learning: A Causal Perspectivecited by 76
  11. 2019dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairscited by 73
  12. 2020Informative Dropout for Robust Representation Learning: A Shape-bias Perspectivecited by 57
  13. 2022Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspectivecited by 48
  14. 2021CausalAdv: Adversarial Robustness through the Lens of Causalitycited by 37
  15. 2022Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loopcited by 30
  16. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  17. 2017Causally Regularized Learning with Agnostic Data Selection Biascited by 29
  18. 2023Invariant Learning via Probability of Sufficient and Necessary Causescited by 22
  19. 2023Towards Trustworthy Explanation: On Causal Rationalizationcited by 19
  20. 2023Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regressioncited by 18
  21. 2023On Learning Necessary and Sufficient Causal Graphscited by 14
  22. 2021Adversarial Visual Robustness by Causal Interventioncited by 13
  23. 2021Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustnesscited by 11
  24. 2023Specify Robust Causal Representation from Mixed Observationscited by 3

Built on by

Not cited yet.