论文标题
Borex：图像和视频分类模型的显着性图基于贝叶斯优化的优化
BOREx: Bayesian-Optimization--Based Refinement of Saliency Map for Image- and Video-Classification Models
论文作者
论文摘要
解释图像和视频分类模型产生的分类结果是计算机视觉中重要但充满挑战的问题之一。已经提出了许多用于为此目的产生基于热图的解释的方法，包括基于使用模型内部信息（例如LRP，Grad-CAM和Grad-CAM和Grad-CAM ++）的白色框方法的方法，以及基于不使用任何内部信息的黑盒方法（例如，Lime，Shap和Sib）。我们提出了一种新的黑盒方法Borex（贝叶斯优化，用于完善视觉模型解释），以完善任何方法产生的热图。我们的观察结果是，基于热图的解释可以看作是基于贝叶斯优化的解释方法的先验。基于这一观察结果，Borex进行高斯过程回归（GPR），以估计给定图像中每个像素的显着性，从另一种解释方法产生的图像开始。从统计学上讲，我们的实验表明，Borex的改进可改善图像和视频分类结果的低质量热图。
Explaining a classification result produced by an image- and video-classification model is one of the important but challenging issues in computer vision. Many methods have been proposed for producing heat-map--based explanations for this purpose, including ones based on the white-box approach that uses the internal information of a model (e.g., LRP, Grad-CAM, and Grad-CAM++) and ones based on the black-box approach that does not use any internal information (e.g., LIME, SHAP, and RISE). We propose a new black-box method BOREx (Bayesian Optimization for Refinement of visual model Explanation) to refine a heat map produced by any method. Our observation is that a heat-map--based explanation can be seen as a prior for an explanation method based on Bayesian optimization. Based on this observation, BOREx conducts Gaussian process regression (GPR) to estimate the saliency of each pixel in a given image starting from the one produced by another explanation method. Our experiments statistically demonstrate that the refinement by BOREx improves low-quality heat maps for image- and video-classification results.
