A web application that classifies an uploaded image into a disaster type, utilizing Angular

Deep Learning for SAR Ship classification: Focus on Unbalanced Datasets and Inter-Dataset Generalization

Histopathologic metastatic breast cancer detection with convolution neural networks on pathology whole slide images using TensorFlow.

One of the firsts dataset level explanability libraries for 1d signal using GRAD-CAM++

Fellowship.AI Challenge: Cohort 19

Visualizing the decision making process of models - for melanoma detection

Implementation of Gradient-weighted Class Activation Maps of a simple classifier in Tensorflow. In progress.

Medical Diagnosis in Chest X-ray images.

This notebook demonstrates a number of saliency mask techniques, augmented with the SmoothGrad technique, using the VGG16, AlexNet, InceptioNet, MobileNet convolutional neural network in TF2.

Grad-CAM implementation in TensorFlow JS.

This repository contains a CIFAR-10 dataset classification project alongside GradCAM implementation

Diagnose the presence of skin cancer in a person using CNN and as well explain what led the CNN to arrive at the decision. Visual explanations are made utilizing the Gradient-weighted Class Activation Mapping (Grad-CAM), the gradients flowing into the final convolutional layer to produce a coarse localization map highlighting the important regio…

2023 GradCam - DMKD

SharePoint Webpart (SPFx) VGG16 Internal Activations and CAM Heatmap.

Analyzing the Effect of Adversarial Inputs on Saliency Maps

Class Activation Map (CAM and Grad-CAM) Analysis of fine-tuned CNNs with transfer learning for Pokemon classification task to understand the features learned by deep CNN

TeleXGI: Explainable Gastrointestinal Image Classification for TeleSurgery Systems

This is the public version of my master's research work.

Analysis of visualization methods for relevant areas within images for a trained CNN. Used the GTSRB dataset as well as Activation Maximization, Saliency Map, GradCam, and Gradcam++ methods.

Chest x-ray classifier to diagnose between covid-19 infected lungs, viral pneumonia and healthy lungs using deep learning.