改进梯度可视化方法，让模型注意力更聚焦于关键细节。
HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations
- 利用所有卷积层激活图自适应生成注意力图
- 在物体分类任务中显著优于LayerCAM和Grad-CAM
- 适合需要精准解释视觉决策的AI应用
深度学习模型参数量可达数十亿，难以解释其内部转换与输出。由于人工智能在关键场景中的应用日益广泛，可解释性变得愈发重要。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LayerCAM方法，提出改进方法HiRA-CAM。该方法通过自适应融合网络所有层的激活图，生成更聚焦的显著性图，在物体分类任务中表现优于LayerCAM和Grad-CAM。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。