Some visual explanation methods.

Description: Only Do backward
url: https://github.com/huangchuanhong/VisualExplanationMethods/blob/master/grad-cam-pytorch/grad_cam.py   class BackPropation
origin github: https://github.com/kazuto1011/grad-cam-pytorch

Description: When Do backward, exchange Relu backward with Relu.
url: 1.https://github.com/huangchuanhong/VisualExplanationMethods/tree/master/VisualizingCNN
2.https://github.com/huangchuanhong/VisualExplanationMethods/blob/master/grad-cam-pytorch/grad_cam.py   class Deconvnet
paper: 2014 ECCV paper "Visualizing and understanding convolutional networks"
paper url: https://arxiv.org/abs/1311.2901
origin github 1.https://github.com/huybery/VisualizingCNN
2.https://github.com/kazuto1011/grad-cam-pytorch

Description: When Do backward, add a Relu after each Relu backward.
url: https://github.com/huangchuanhong/VisualExplanationMethods/blob/master/grad-cam-pytorch/grad_cam.py   class GuidedBackPropatation
paper: "Striving for simplicity: The All Convolutional net"
paper url: https://arxiv.org/abs/1412.6806
origin github: https://github.com/kazuto1011/grad-cam-pytorch

url: https://github.com/huangchuanhong/VisualExplanationMethods/tree/master/CAM
paper: 2016 CVPR paper "Learning Deep Features for Discriminative Localization"
paper url: https://arxiv.org/abs/1512.04150
origin github: https://github.com/zhoubolei/CAM/blob/master/pytorch_CAM.py

url: https://github.com/huangchuanhong/VisualExplanationMethods/tree/master/grad-cam-pytorch/grad_cam.py   class GradCAM
paper: Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
paper url: https://arxiv.org/abs/1610.02391
origin github: https://github.com/kazuto1011/grad-cam-pytorch

url: https://github.com/huangchuanhong/VisualExplanationMethods/blob/master/sam
paper: "SAM: The Sensitivity of Attribution Methods to Hyperparameters"
paper url: https://arxiv.org/abs/2003.08754
origin github: https://github.com/anguyen8/sam

url: 1.https://github.com/huangchuanhong/VisualExplanationMethods/tree/master/lime_example
2.https://github.com/huangchuanhong/VisualExplanationMethods/blob/master/sam/LIME_Madry.py
paper: "Why should I trust you? Explaining the Predictions of Any Classifier"
paper url: https://arxiv.org/abs/1602.04938
origin github: https://github.com/anguyen8/sam

url: https://github.com/huangchuanhong/VisualExplanationMethods/blob/master/sam/MP_MADRY.py
paper: "Interpretable Explanations of Black Boxes by Meaningful Perturbation"
paper url: https://arxiv.org/abs/1704.03296
origin github: https://github.com/anguyen8/sam

url: https://github.com/huangchuanhong/VisualExplanationMethods/blob/master/sam
paper: "SAM: The Sensitivity of Attribution Methods to Hyperparameters"
paper url: https://arxiv.org/abs/2003.08754
origin github: https://github.com/anguyen8/sam

url: https://github.com/huangchuanhong/VisualExplanationMethods/blob/master/sam
paper: "SAM: The Sensitivity of Attribution Methods to Hyperparameters"
paper url: https://arxiv.org/abs/2003.08754
origin github: https://github.com/anguyen8/sam