Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

A tool for classifying an image into a disaster type, utilizing Python

This repository provides the training codes to classify aerial images using a custom-built model (transfer learning with InceptionResNetV2 as the backbone) and explainers to explain the predictions with LIME and GradCAM on an interface that lets you upload or paste images for classification and see visual explanations.

Multi-classification of ocular diseases using ODIR-5K and uses explainable AI methods to improve the transparency of computer aided diagnostic systems.

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

A multi-functional library for full-stack Deep Learning. Simplifies Model Building, API development, and Model Deployment.

Neural network visualization toolkit for tf.keras

Filter visualization, Feature map visualization, Guided Backprop, GradCAM, Guided-GradCAM, Deep Dream

Implementation of GradCAM & Guided GradCAM with Tensorflow 2.x

An implemention of CLIP-ViL Gradcam for VQA tasks

A library that helps to explain AI models in a really quick & easy way

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.

Anomaly Detection in Optical Networks

This repository contains all the work that I regularly did and studied from Medium blogs, several research papers, and other Repos (related/unrelated to the research papers).

Content-Based Image Retrieval (CBIR) is a significant field within computer vision that empowers efficient exploration and retrieval of images based on their visual content.

Schizophrenia detection using wavelet transforms plus gradcam explainability on the scalograms

This respositoy showcases the implementation of the transfer learning approach on the ResNet50 model for the detection of Covid-19 in the X-Ray lung images. Additionally, heatmaps were generated to show affected portion of the lungs via the Grad-CAM technique.

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.

Wanna know what your model sees? Here's a package for applying EigenCAM on the new YOLO V8 model