视觉模型归因质量基准测试
Benchmarking the Attribution Quality of Vision Models
AI总结：
该研究提出新型评估协议解决增量删除协议的域外与模型间不可比问题，评估23种归因方法及视觉骨干设计对归因质量的影响，发现内在可解释模型更优、部分标准设计可提升归因质量。
摘要：
归因图是解释计算机视觉模型运行机制最成熟的工具之一，它为输入特征分配重要性分数，表明每个特征对深度神经网络预测结果的相关程度。尽管大量研究致力于提出新的归因方法，但对这些方法的合理评估仍是一项艰巨挑战。本研究提出了一种全新的评估协议，克服了被广泛使用的增量删除协议的两个根本局限：域外问题和缺乏模型间可比性。借助该协议，我们评估了23种归因方法，以及主流视觉骨干网络的不同设计选择对其归因质量的影响。研究发现，内在可解释模型的表现优于标准模型，且原始归因值展现出的归因质量比以往研究结论所显示的更高。此外，我们发现改变网络设计时，归因质量会出现一致性变化，表明部分标准设计选择能够提升归因质量。
英文摘要：
Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how relevant each feature is for the prediction of a deep neural network. While much research has gone into proposing new attribution methods, their proper evaluation remains a difficult challenge. In this work, we propose a novel evaluation protocol that overcomes two fundamental limitations of the widely used incremental-deletion protocol, i.e., the out-of-domain issue and lacking inter-model comparisons. This allows us to evaluate 23 attribution methods and how different design choices of popular vision backbones affect their attribution quality. We find that intrinsically explainable models outperform standard models and that raw attribution values exhibit a higher attribution quality than what is known from previous work. Further, we show consistent changes in the attribution quality when varying the network design, indicating that some standard design choices promote attribution quality.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
