mlsanityData to 7 Oct 2026

A Causal Framework for Aligning Image Quality Metrics and Deep Neural Network Robustness

arXiv 2503.02797 ↗First posted 4 Mar 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Image quality plays an important role in the performance of deep neural networks (DNNs) that have been widely shown to exhibit sensitivity to changes in imaging conditions. Conventional image quality assessment (IQA) seeks to measure and align quality relative to human perceptual judgments, but we often need a metric that is not only sensitive to imaging conditions but also well-aligned with DNN sensitivities. We first ask whether conventional IQA metrics are also informative of DNN performance. We show theoretically and empirically that conventional IQA metrics are weak predictors of DNN performance for image classification. Using our causal framework, we then develop metrics that exhibit strong correlation with DNN performance, thus enabling us to effectively estimate the quality distribution of large image datasets relative to targeted vision tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 46 of its 70 references that are in the map. First posted on arXiv 4 Mar 2025.

Builds on

46 of 70 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  7. 2022A ConvNet for the 2020scited by 3,545
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2019Searching for MobileNetV3cited by 1,984
  11. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  12. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
34 more
  1. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  2. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  3. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  4. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  5. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  6. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
  7. 2018Confounding variables can degrade generalization performance of radiological deep learning modelscited by 374
  8. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  9. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 301
  10. 2020No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problemscited by 208
  11. 2022Datamodels: Predicting Predictions from Training Datacited by 186
  12. 2021Partial success in closing the gap between human and machine visioncited by 185
  13. 2022Domino: Discovering Systematic Errors with Cross-Modal Embeddingscited by 155
  14. 2016Understanding How Image Quality Affects Deep Neural Networkscited by 118
  15. 2020On Robustness and Transferability of Convolutional Neural Networkscited by 98
  16. 2023ARNIQA: Learning Distortion Manifold for Image Quality Assessmentcited by 87
  17. 2018Automated Data Slicing for Model Validation:A Big data - AI Integration Approachcited by 70
  18. 2023Data Pruning via Moving-one-Sample-outcited by 67
  19. 2023Large-scale Dataset Pruning with Dynamic Uncertaintycited by 63
  20. 2022Detecting Shortcut Learning for Fair Medical AI using Shortcut Testingcited by 52
  21. 2022Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experimentscited by 50
  22. 2021A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?cited by 48
  23. 2021OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Imagescited by 46
  24. 2024Effective pruning of web-scale datasets based on complexity of concept clusterscited by 34
  25. 2019Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?cited by 25
  26. 2019Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slicescited by 23
  27. 2022The Robustness Limits of SoTA Vision Models to Natural Variationcited by 15
  28. 2024Dataset Difficulty and the Role of Inductive Biascited by 12
  29. 2023Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?cited by 10
  30. 2021Using Synthetic Corruptions to Measure Robustness to Natural Distribution Shiftscited by 7
  31. 2023RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-centric Learningcited by 6
  32. 2023Data AUDIT: Identifying Attribute Utility- and Detectability-Induced Bias in Task Modelscited by 4
  33. 2024From Generalization to Precision: Exploring SAM for Tool Segmentation in Surgical Environmentscited by 3
  34. 2024Causality-Driven Audits of Model Robustnesscited by 2

Built on by

Not cited yet.