Rigorousness and clarity are both essential for interpretations of DNNs to engender human trust. Path methods are commonly employed to generate rigorous attributions that satisfy three axioms. However, the meaning of attributions remains ambiguous due to distinct path choices. To address the ambiguity, we introduce \textbf{Concentration Principle}, which centrally allocates high attributions to indispensable features, thereby endowing aesthetic and sparsity. We then present \textbf{SAMP}, a model-agnostic interpreter, which efficiently searches the near-optimal path from a pre-defined set of manipulation paths. Moreover, we propose the infinitesimal constraint (IC) and momentum strategy (MS) to improve the rigorousness and optimality. Visualizations show that SAMP can precisely reveal DNNs by pinpointing salient image pixels. We also perform quantitative experiments and observe that our method significantly outperforms the counterparts. Code: https://github.com/zbr17/SAMP.

翻译：严格性与清晰性对于深度神经网络解释以赢得人类信任均至关重要。路径方法常被用于生成满足三条公理的严格归因，但因路径选择不同，归因含义仍存在歧义。为解决此歧义，我们提出**集中性原则**，该原则将高归因集中于不可或缺的特征，从而赋予美学性与稀疏性。随后，我们提出**SAMP**——一种模型无关的解释器，可从预定义的操控路径集合中高效搜索近似最优路径。此外，我们提出无穷小约束(IC)与动量策略(MS)以提升严格性与最优性。可视化结果表明，SAMP可通过精确定位显著图像像素精确揭示深度神经网络。定量实验显示，我们的方法显著优于对比方法。代码：https://github.com/zbr17/SAMP。