基于谱分解的梯度积分法，实现从粗到细的特征归因。
Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution
- 利用输入与基线差值的SVD分解构建逐步激活的积分路径
- 在多个图像数据集上生成更清晰、噪声更低的归因图
- 适合需要高精度特征解释的视觉模型分析场景
集成梯度（IG）是一种广泛采用的特征归因方法，满足理想的公理性质。然而，积分路径的选择显著影响归因质量，标准直线路径会同时引入所有输入特征，常导致噪声梯度累积。为解决此问题，我们提出谱集成梯度（SIG），基于基线到输入差异的奇异值分解（SVD）构建积分路径。通过按奇异分量从大到小逐步激活，SIG先引入全局结构再呈现细节，自然遵循由粗到细的进程。在多个图像分类数据集上的广泛评估表明，SIG生成的归因图更清晰、噪声更少，并在定量性能上优于现有路径相关归因方法。代码已公开于 https://github.com/leekwoon/sig/。
原文摘要 · Abstract (English)
Integrated Gradients (IG) is a widely adopted feature attribution method that satisfies desirable axiomatic properties. However, the choice of integration path significantly affects the quality of attributions, and the standard straight-line path introduces all input features simultaneously, often accumulating noisy gradients along the way. To address this limitation, we propose Spectral Integrated Gradients, which constructs integration paths based on singular value decomposition (SVD) of the baseline-to-input difference. By progressively activating singular components from largest to smallest, SIG introduces global structure before fine-grained details, naturally following a coarse-to-fine progression. Through extensive evaluation across diverse image classification datasets, we demonstrate that SIG produces cleaner attribution maps with reduced noise and achieves improved quantitative performance compared to existing path-based attribution methods. Our code is available at https://github.com/leekwoon/sig/.
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。