Boundary box creation using a GradCAM heat-map from a pre-trained image classification model.

Making CNNs interpretable.

One of the first implementations of Grad-CAM ++ for time series / 1d signal.

Frame-agnostic XAI Library for Computer Vision, for understanding why models behave that way.

The Basic Classification

An API to better understand and visualize the inner workings of a CNN with GradCam; currently MobileNet

First position in Gran Canary Datathon 2021

Applying GradCAM method with 3 kinds of CNN-based model for NLP classification task on french dataset.

Three different DNN models Xception, In- ceptionV3, and VGG19 were used for the classification of crop disease from the image dataset, and explainable AI XAI was used to evaluate their performance. InceptionV3 was achieved as the best model with the highest accuracy of 97.20% accuracy.

Weakly Object Localization Using Grad-CAM method

This repository consists of models of CNN for classifying different types of charts. Moreover, it also includes script of fine-tuned VGG16 for this task. On top of that CradCAM implementation of fine-tuned VGG16.

Example of how to use MATLAB to produce post-hoc explanations (using Grad-CAM and image LIME) for a medical image classification task.

CNN architectures Resnet-50 and InceptionV3 have been used to detect whether the CT scan images is covid affected or not and prediction is validated using explainable AI frameworks LIME and GradCAM.

Example of how to use MATLAB to produce post-hoc explanations (using Grad-CAM) for image classification tasks.

CIFAR10 image recognition using ResNet architecture, Gradcam images

Developed a CNN model to classify skin moles as benign or malignant using a balanced dataset from Kaggle, achieving a test accuracy of 81.82% and an AUC of 89.06%. Implemented data preprocessing by resizing images to 224x224 pixels and normalizing pixel values, enhancing model performance and stability.