This project aims to predict the age of individuals from images using a pre-trained ResNet50 model. We preprocess the dataset, train the model, and visualize the results using Grad-CAM.

A project for lung disease detection and analysis using deep learning. It includes lung segmentation, disease classification, and severity localization with Grad-CAM for visual explanations. This repository provides code, datasets, and documentation for replication and further research.

Based on the mmdetection framework, compute various salience maps for object detection.

Leveraging the power of transfer learning using the VGG19 network within TensorFlow to tackle the specific problem of image classification.

A standalone desktop application for image classification with visualization and reporting

ISIC2019 skin lesion classification (binary & multi-class) as well as segmentation pipelines using VGG16_BN and visual attention blocks. The project features improving the results found in the literature by implementing an ensemble architecture. This project was developed for "Computer Aided Diagnosis - CAD" course for MAIA masters program.

Using four different CNN architectures in an endeavor to detect built heritage in need of preservation and approximately localize the existent damage therein using the GradCam technique.

This repository aims to implement a mushroom type classifier using PyTorch, utilizing various models to enhance performance. Additionally, the project includes an analysis of the model's performance using Gradient-Class Activation Map (Grad-CAM) visualization.

Disease diagnoses in chest radiographs with different neural network architectures, and models activations localization using grad-cam. The whole implementation is in Pytorch.

This repository explores the fascinating world of brain tumor classification using cutting-edge Convolutional Neural Networks (CNNs) and eXplainable Artificial Intelligence (XAI) techniques.

FellowshipAi project

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.

cnn model interpretablity

This repo is special for those who want to start learning computer vision related tasks such as image classification.

Paper under review on "Multimedia Tools and Applications" journal.

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

A CT-scan of your CNN

MNIST classification and visualize class activation maps with Pytorch.

A script to generate grad-cam pictures for Apple chip.

Interpretable Computer Vision: Visualising the zones of steepest gradients in the last convolutional layer