The doi above is for this specific version of this collection, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
doi: 10.4121/6c70718d-cd47-46b2-92cc-d020c4f70fe7

Balayn, Agathe (2023): Set of datasets for evaluating explainability methods of computer vision models (deep learning-based). Version 1. 4TU.ResearchData. collection. https://doi.org/10.4121/6c70718d-cd47-46b2-92cc-d020c4f70fe7.v1

Collection

• Artificial Intelligence and Image Processing
• Information and Computing Sciences

biases, computer vision, deep learning, explainability, ground truth explanations, machine learning

by Agathe Balayn

This collection of datasets (image samples, ground truth per sample, extraction of saliency maps and potential manual, semantic annotations of the saliency maps) has been used to quantitatively and qualitatively evaluate explainability methods for computer vision, deep-learning-based, models.

• 2023-03-29 first online, published, posted

4TU.ResearchData

• https://doi.org/10.1145/3491102.3517474
• https://doi.org/10.1145/3442381.3450069
• https://doi.org/10.1145/3544548.3581555

Delft University of Technology