论文标题
使用模型 - 敏捷方法生成详细的显着图
Generating detailed saliency maps using model-agnostic methods
论文作者
论文摘要
可解释的人工智能的新兴领域着重于研究解释复杂机器学习模型的决策过程的方法。在计算机视觉的解释性领域中，提供了解释为显着图，从而可视化了输入W.R.T.单个像素的重要性。模型的预测。在这项工作中，我们着重于一种称为Rise的基于扰动的，模型的解释性方法，详细阐述了基于网格的方法的缺点，并提出了两种修改：基于凸多边形闭塞的正方形闭塞的替换基于Voronoi网状细胞的细胞，并增加了voronoi网细胞的细胞，并增加了对胶粘剂的信息保证。这些修改统称为Vrise（Voronoi-Rise），分别旨在在采样密度非常低或非常高的情况下，分别提高使用大型遮挡和加速显着性图的加速显着性图所产生的地图的准确性。我们使用显着性引导的内容插入/缺失度量标准和基于边界框的本地化度量进行了定量比较Vrise和Vrise在ILSVRC2012的验证拆分中产生的显着性图的准确性。此外，我们探索了可配置的遮挡模式参数的空间，以更好地了解它们对Rise和Vrise产生的显着图的影响。我们还描述并证明了在实验过程中观察到的两种效果，这是由于上升的随机抽样方法引起的：“特征切片”和“显着性错误”。我们的结果表明，凸多边形遮挡可为粗咬合网格和多对象图像产生更准确的地图，但在其他情况下不能保证改进。显示信息保证可以提高收敛速率，而不会产生大量的计算开销。
The emerging field of Explainable Artificial Intelligence focuses on researching methods of explaining the decision making processes of complex machine learning models. In the field of explainability for Computer Vision, explanations are provided as saliency maps, which visualize the importance of individual pixels of the input w.r.t. the model's prediction. In this work we focus on a perturbation-based, model-agnostic explainability method called RISE, elaborate on observed shortcomings of its grid-based approach and propose two modifications: replacement of square occlusions with convex polygonal occlusions based on cells of a Voronoi mesh and addition of an informativeness guarantee to the occlusion mask generator. These modifications, collectively called VRISE (Voronoi-RISE), are meant to, respectively, improve the accuracy of maps generated using large occlusions and accelerate convergence of saliency maps in cases where sampling density is either very low or very high. We perform a quantitative comparison of accuracy of saliency maps produced by VRISE and RISE on the validation split of ILSVRC2012, using a saliency-guided content insertion/deletion metric and a localization metric based on bounding boxes. Additionally, we explore the space of configurable occlusion pattern parameters to better understand their influence on saliency maps produced by RISE and VRISE. We also describe and demonstrate two effects observed over the course of experimentation, arising from the random sampling approach of RISE: "feature slicing" and "saliency misattribution". Our results show that convex polygonal occlusions yield more accurate maps for coarse occlusion meshes and multi-object images, but improvement is not guaranteed in other cases. The informativeness guarantee is shown to increase the convergence rate without incurring a significant computational overhead.
