Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

knowledge-base-3

Explainable Artificial Intelligence (XAI)

3260 papers • 126 benchmarks • 313 datasets

Explainable Artificial Intelligence

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in explainable-artificial-intelligence-xai-3

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find explainable-artificial-intelligence-xai-3 models and implementations

Datasets

XImageNet-12

SpanEX

Subtasks

No subtasks available.

Most implemented papers

RISE: Randomized Input Sampling for Explanation of Black-box Models

Kate Saenko, Abir Das, Vitali Petsiuk•Mon Jun 18 2018

The problem of Explainable AI for deep neural networks that take images as input and output a class probability is addressed and an approach called RISE that generates an importance map indicating how salient each pixel is for the model's prediction is proposed.

1383

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Software for dataset-wide XAI: From local explanations to global insights with Zennit, CoRelAy, and ViRelAy

K. Müller, W. Samek, S. Lapuschkin, Christopher J. Anders, David Neumann•Wed Jun 23 2021

Three software packages designed to facilitate the exploration of model reasoning using attribution approaches and beyond are presented, aiming to promote reproducibility in the field and empower scientists and practitioners to uncover the intricacies of complex model behavior.

82 0

Paper Graph

Contrastive Explanations with Local Foil Trees

Mark Antonius Neerincx, J. V. D. Waa, M. Robeer, J. Diggelen, Matthieu J. S. Brinkhuis•Mon Jun 18 2018

This paper utilizes the human tendency to ask questions to reduce the number of features to those that play a main role in the asked contrast to identify the disjoint set of rules that causes the tree to classify data points as the foil and not as the fact.

88 0

Paper Graph

AudioMNIST: Exploring Explainable Artificial Intelligence for audio analysis on a simple benchmark

W. Samek, Sören Becker, Johanna Vielhaben, M. Ackermann, Klaus Müller, S. Lapuschkin•Sun Jul 08 2018

A novel Open Source audio dataset is presented consisting of 30,000 audio samples of English spoken digits which is used for classification tasks on spoken digits and speakers' biological sex and demonstrates the superior interpretability of audible explanations over visual ones in a human user study.

147 0

Paper Graph

Do Not Trust Additive Explanations

P. Biecek, Alicja Gosiewska•Tue Mar 26 2019

This paper examines the behavior of the most popular instance-level explanations under the presence of interactions, introduces a new method that detects interactions for instance- level explanations, and performs a large scale benchmark to see how frequently additive explanations may be misleading.

55 0

Paper Graph

TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP

Isabelle Augenstein, Nils Rethmeier, V. Saxena•Sun Dec 01 2019

The established computer vision explainability principle of 'visualizing preferred inputs of neurons' is modified to make it usable transfer analysis and NLP, and TX-Ray expresses neurons as feature preference distributions to quantify fine-grained knowledge transfer or adaptation and guide human analysis.

23 0

Paper Graph

Quantifying Explainability of Saliency Methods in Deep Neural Networks With a Synthetic Dataset

Cuntai Guan, Erico Tjoa•Sun Sep 06 2020

A synthetic dataset that can be generated adhoc along with the ground-truth heatmaps for more objective quantitative assessment of different XAI methods is introduced and mabCAM is introduced as the heatmap generation method compatible with the authors' ground- Truth heatmaps.

33 0

Paper Graph

Adding a benchmark result helps the community track progress.

Explainable Artificial Intelligence (XAI) | State-of-the-Art