This project propose a simple example to expose the implicit attention of Convolutional Neural Networks on the image.

I implemented a detection algorithm with a classification data set that does not have annotation information for the bounding box. Based on resnet50 network, I implemented text detector using class activation mapping method.

Class Activation Map using Keras

Visualizing where the Convolution Network is looking through CAM.

TensorFlow implementations of visualization of convolutional neural networks, such as Grad-Class Activation Mapping and guided back propagation

Tutorial to show how to extract object localization

Evaluating surgical skills from kinematic data using convolutional neural networks

VGG transfer learning and Class Activation Mapping

Class-Weighted Convolutional Features for Image Retrieval (BMVC 2017)

saliency map, adversarial image, (gradient) class activation map

Generates class activation maps for CNN's with Global Average Pooling Layer Keras

A Deep Learning Humerus Bone Fracture Detection Model which classifies a broken humerus bone X-ray image from a normal X-ray image with no fracture using Back Propagation, Regularization, Convolutional Neural Networks (CNN), Auto-Encoders (AE) and Transfer Learning.

Class activation maps for high risk and low risk patients in lung adenocarcinoma

Building a multi-label classifier from scratch and using transfer learning for the PASCAL VOC image dataset.

Special Project - CA classification (2019 Fall)

MVA Master School Project - Weakly Supervised Semantic Segmentation

Visualizing Class Activation Maps for Convolutional Neural Networks

High Resolutions Class Activation Maps usage script. Implementation from HR-CAM paper.

Weakly supervised Classification and Localization of Chest X-ray images