论文标题
M3D-CAM：一个生成3D数据注意图的Pytorch库，用于医学深度学习
M3d-CAM: A PyTorch library to generate 3D data attention maps for medical deep learning
论文作者
论文摘要
M3D-CAM是一个易于使用的库来生成基于CNN的Pytorch模型的注意图，可改善对人类模型预测的可解释性。可以使用多种方法来生成注意力图，例如引导反向传播，GRAD-CAM，引导Grad-CAM和Grad-CAM ++。这些注意力图可视化在一定层上影响模型预测最大的输入数据中的区域。此外，M3D-CAM支持分类任务以及分割的2D和3D数据。一个关键功能也是，在大多数情况下，仅需要一行代码来生成注意力图基本上插入M3D-CAM。
M3d-CAM is an easy to use library for generating attention maps of CNN-based PyTorch models improving the interpretability of model predictions for humans. The attention maps can be generated with multiple methods like Guided Backpropagation, Grad-CAM, Guided Grad-CAM and Grad-CAM++. These attention maps visualize the regions in the input data that influenced the model prediction the most at a certain layer. Furthermore, M3d-CAM supports 2D and 3D data for the task of classification as well as for segmentation. A key feature is also that in most cases only a single line of code is required for generating attention maps for a model making M3d-CAM basically plug and play.
