HiRA-CAM：在基于梯度的视觉解释中保留细粒度空间相关性
HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations
- University of Cincinnati（辛辛那提大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文针对CNN可解释性问题，提出基于LayerCAM改进的HiRA-CAM方法，通过自适应利用CNN各层激活图生成更聚焦的显著性图，其在物体分类任务的显著性图生成上优于LayerCAM与Grad-CAM。
AI中文摘要：
深度学习模型可包含数十亿乃至更多参数，这使得解释其内部变换与输出变得困难，但由于AI在关键应用中的使用，可解释性的重要性日益提升。本文聚焦卷积神经网络（CNN）的可解释性，基于流行的基于梯度的CNN内部特征提取方法LayerCAM，提出一种名为HiRA-CAM的改进方法，实验表明该方法在生成用于物体分类的有效显著性图方面，性能优于LayerCAM和Grad-CAM。HiRA-CAM的核心特征是自适应利用CNN所有层的激活图，以生成更聚焦的显著性图。
英文摘要：
Deep Learning models can include billions of parameters or more, making it difficult to explain their internal transformations and outputs. However, explainability is increasing in importance due to the use of AI in crucial applications. This paper focuses on the interpretability of convolutional neural networks (CNNs). Building on the popular gradient based method LayerCAM for extracting internal features in CNNs, we propose an improved method named HiRA-CAM, and show that it outperforms both LayerCAM and Grad-CAM on creating useful saliency maps for object classification. The main feature of HiRA-CAM is its adaptive use of activation maps from all the layers of the CNN to arrive at a more focused saliency map.
