cff-version: 1.2.0
abstract: "<p><span style="background-color: rgb(255, 250, 234);">Set of datasets of images, their ground truth, their saliency map for one model, and the manual annotations of the saliency maps with semantic concepts of various granularities. The images in each set were selected in order to inject class-specific biases in the dataset.</span></p><ul><li><span style="background-color: rgb(255, 250, 234);">One set consists of two classes sampled from ImageNet, representing ambulances and vans.</span></li><li><span style="background-color: rgb(255, 250, 234);">One set consists of two classes sampled from PA-100K, representing human males and females.</span></li><li><span style="background-color: rgb(255, 250, 234);">4 sets consists of three classes extracted from ImageNet, lobsters, sharks, and trouts, sampled in different ways to include various biases.</span></li></ul>"
authors:
  - family-names: Balayn
    given-names: Agathe
title: "Datasets for the evaluation of explainability methods for computer vision models"
keywords:
version: 1
identifiers:
  - type: doi
    value: 10.4121/c5831e59-8e02-444d-b753-99371b93724e.v1
license: CC BY-NC 4.0
date-released: 2023-03-30