Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Official implementation of Score-CAM in PyTorch

Deep functional residue identification

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

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

Class Activation Map using Keras

COVID-CXNet: Diagnosing COVID-19 in Frontal Chest X-ray Images using Deep Learning. Preprint available on arXiv: https://arxiv.org/abs/2006.13807

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.

This repository introduces different Explainable AI approaches and demonstrates how they can be implemented with PyTorch and torchvision. Used approaches are Class Activation Mappings, LIMA and SHapley Additive exPlanations.

Evaluating surgical skills from kinematic data using convolutional neural networks

Code for the paper : "Weakly supervised segmentation with cross-modality equivariant constraints", available at https://arxiv.org/pdf/2104.02488.pdf

Visualizing where the Convolution Network is looking through CAM.

【瑞士军刀般的工具】用最短的代码完成对模型的分析，包含 ImageNet Val、FLOPs、Params、Throuthput、CAM 等

VGG transfer learning and Class Activation Mapping

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.

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

Scripts that utilize class activation maps and self-attention layers within Keras models to classify faces from FEI Faces Dataset

Weakly supervised Classification and Localization of Chest X-ray images

Saliency Enhancing with Scaling and Sliding

Code and data for our learning-based eXplainable AI (XAI) method TAME: M. Ntrougkas, N. Gkalelis, V. Mezaris, "TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks", Proc. IEEE Int. Symposium on Multimedia (ISM), Naples, Italy, Dec. 2022.