其他分享
首页 > 其他分享> > CAM(类激活映射),卷积可视化,神经网络可视化,一个库搞定,真的简单的不能再简单

CAM(类激活映射),卷积可视化,神经网络可视化,一个库搞定,真的简单的不能再简单

作者:互联网

https://blog.csdn.net/u014264373/article/details/116302678
方法 它能做什么
GradCAM Weight the 2D activations by the average gradient
GradCAM++ Like GradCAM but uses second order gradients
XGradCAM Like GradCAM but scale the gradients by the normalized activations
AblationCAM Zero out activations and measure how the output drops (this repository includes a fast batched implementation)
ScoreCAM Perbutate the image by the scaled activations and measure how the output drops
EigenCAM Takes the first principle component of the 2D Activations (no class discrimination, but seems to give great results)
EigenGradCAM Like EigenCAM but with class discrimination: First principle component of Activations*Grad. Looks like GradCAM, but cleaner

标签:Like,卷积,GradCAM,but,Activations,可视化,CAM,measure,activations
来源: https://www.cnblogs.com/icemiaomiao3/p/15217130.html