A Causal Framework for Aligning Image Quality Metrics and Deep Neural Network Robustness
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915427705159680 |
|---|---|
| author | Drenkow, Nathan Unberath, Mathias |
| author_facet | Drenkow, Nathan Unberath, Mathias |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02797 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Causal Framework for Aligning Image Quality Metrics and Deep Neural Network Robustness Drenkow, Nathan Unberath, Mathias Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | A Causal Framework for Aligning Image Quality Metrics and Deep Neural Network Robustness |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.02797 |