提出因果框架，让图像质量评估更贴合深度神经网络的鲁棒性表现。
A Causal Framework for Aligning Image Quality Metrics and Deep Neural Network Robustness
- 构建因果模型，分析图像质量与DNN性能间的关联机制。
- 新指标与DNN性能相关性显著提升，可精准评估大规模数据集质量。
- 适合关注模型鲁棒性与数据质量对齐的研究者使用。
图像质量在深度神经网络（DNN）性能中起关键作用，而现有DNN对成像条件变化敏感。传统图像质量评估（IQA）旨在匹配人类感知判断，但常无法有效反映DNN对图像变化的敏感程度。本文首先验证传统IQA指标对图像分类任务中DNN性能的预测能力较弱。随后，基于提出的因果框架，开发出与DNN性能高度相关的新型质量度量，能有效估计大规模图像数据集在特定视觉任务下的质量分布。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。