Official implementation of Score-CAM in PyTorch

Pytorch Implementation of recent visual attribution methods for model interpretability

Model Agnostics breakDown plots

A toolkit for efficent computation of saliency maps for explainable AI attribution. This tool was developed at Lawrence Livermore National Laboratory.

Local Interpretable (Model-agnostic) Visual Explanations - model visualization for regression problems and tabular data based on LIME method. Available on CRAN

[ICCVW 2019] PyTorch code for Class Visualization Pyramid for intpreting spatio-temporal class-specific activations throughout the network

A XAI Framework to provide Contrastive Whole-output Explanation for Image Classification.

Similarity Differences and Uniqueness Explainable AI method

Code, model and data for our paper: K. Tsigos, E. Apostolidis, S. Baxevanakis, S. Papadopoulos, V. Mezaris, "Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection", Proc. ACM Int. Workshop on Multimedia AI against Disinformation (MAD’24) at the ACM Int. Conf. on Multimedia Retrieval (ICMR’24), Thailand, June 2024.

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.

Language-Aware Visual Explanations (LAVE) is a framework designed for image classification tasks, particularly focusing on the ImageNet dataset. Unlike conventional methods that necessitate extensive training, LAVE leverages SHAP (SHapley Additive exPlanations) values to provide insightful textual and visual explanations.