AI 中文总结
本文通过logit轨迹分解揭示音频XAI中掩蔽填充导致的轴外位移，证明无填充声学中性且部分掩蔽下41-77%位移为轴外，并指出归因方法存在装置依赖性，残差结构可缓解。
AI 中文摘要
基于扰动的音频分类器XAI方法通常通过掩蔽频谱图区域并将输出变化归因于保留信号来估计特征重要性。然而，这些方法通常假设填充（掩蔽替换）是可忽略的。我们提出logit空间轨迹分解来检验这一假设。一个轴上分量捕获沿连接完全填充（遮蔽）频谱图与完全保留原始频谱图的直线的输出；一个轴外分量捕获垂直位移。我们评估了三种填充、三种音频分类器和1,100个AudioSet片段。我们证明，在完全遮蔽下，没有填充是声学中性的：零填充激活静音，高斯噪声填充激活宽带噪声。在部分掩蔽下，41-77%的输出位移是轴外的，残差方向在掩蔽保留比例上保持稳定，并且特定于每个模型-填充组合。归因方法通过其采样和加权策略不均匀地暴露于轴外位移，揭示了装置依赖性。在轴外残差稳定且低维的情况下，其结构提供了缓解的可能性。
英文摘要
Perturbation-based XAI methods for audio classifiers often estimate feature importance by masking spectrogram regions and crediting output changes to the retained signal. Yet they typically assume the fill (the mask replacement) is negligible. We propose logit-space trajectory decomposition to examine this assumption. An on-axis component captures output along a line connecting the fully filled (occluded) spectrogram to the fully retained original; an off-axis component captures perpendicular displacement. We evaluate across three fills, three audio classifiers, and 1,100 AudioSet clips. We demonstrate that no fill is acoustically neutral under full occlusion: Zero fill activates silence and Gaussian Noise fill activates broadband noise. Under partial masking, 41-77% of output displacement is off-axis, with the direction of the residual stable across mask retention fraction and specific to each model-fill combination. Attribution methods are unevenly exposed to off-axis displacement through their sampling and weighting strategies, revealing apparatus-dependence. Where the off-axis residual is stable and low-dimensional, its structure affords mitigation.
Comments5 pages, 2 figures, 3 tables. Paper status: submitted
