19 datasets found

A dataset for evaluating anomaly explanation methods. It contains 22,722 manually labelled frames in ShanghaiTech, Avenue, and UCSD Ped2.

ConceptDistil is a method to bring concept explanations to any black-box classifier using knowledge distillation.

ConceptDistil is a method to bring concept explanations to any black-box classifier using knowledge distillation.

ConceptDistil is a method to bring concept explanations to any black-box classifier using knowledge distillation.

ConceptDistil is a method to bring concept explanations to any black-box classifier using knowledge distillation.

Do models explain themselves? counterfactual simulatability of natural language explanations

We build two explainable style transfer datasets by augmenting existing datasets with synthetic textual explanations generated by a teacher model.

We build two explainable style transfer datasets by augmenting existing datasets with synthetic textual explanations generated by a teacher model.

We build two explainable style transfer datasets by augmenting existing datasets with synthetic textual explanations generated by a teacher model.

DermXDB is a skin disease diagnosis explainability dataset which enables benchmarking the explainability performance of ConvNet architectures.

Challenge 3 - Blue and Yellow Circles: Set of all possible Kandinsky Figures consist of equal size blue and yellow circles.

Challenge 2 - Nine Circles: Set of Kandinsky Figures consist of 9 circles arranged in a regular grid.

Challenge 1 - Objects and Shapes: Ground truth gt(k) is defined as 'in a Kandinsky Figure small objects are arranged on big shapes same as object shapes, in the big shape of...

Kandinsky Patterns are mathematically describable, simple self-contained hence controllable test data sets for the development, validation and training of explainability in...

The dataset is used for building a music recommendation product with key focus on new song discovery and explainability.

Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive...

The HateXplain dataset is a benchmark dataset for explainable hate speech detection.

ExplainFix adopts two design principles: the “fixed filters” principle that all spatial filter weights of convolutional neural networks can be fixed at initialization and never...

The dataset used in the paper is a collection of images from various sources, including MNIST, EMNIST, CIFAR10, X-ray pneumonia, and Diabetic Retinopathy detection.