by mrgloom

mrgloom / CNN-heatmap
129 Stars 31 Forks Last release: Not found 60 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:


1. Visualizing and Understanding Convolutional Networks

  1. Net surgery trick

convert fully connected layers to their equivalent convolutional layers, since the weights are the same and only the shapes are different.

  1. Global average pooling layer Network In Network

  2. Learning Deep Features for Discriminative Localization

  3. Grad-CAM: Gradient-weighted Class Activation Mapping

  4. Is object localization for free? – Weakly Supervised Object Recognition with Convolutional Neural Networks

Additional: ~~~

  1. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

  2. Top-down NeuralAttention by Excitation Backprop (c-MWP)

  3. Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer

  4. Visualizing Deep Neural Network Decisions: Prediction Difference Analysis A New Method to Visualize Deep Neural Networks

  5. Self-Taught Object Localization with Deep Network

  6. Shallow and Deep Convolutional Networks for Saliency Prediction ~~~

Keras codebase: ~~~

Oclusion based technique:

Net surgery trick:


Grad-CAM ~~~

Tensorflow codebase: ~~~ GAP



PyTorch codebase:



SPN ~~~

Regression Activation Map

Other ~~~

Visualization: ~~~

To look at: ~~~ ~~~

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.