Biased bird image dataset for the evaluation of explainability methods applied to computer vision (deep-learning-based) models

doi: 10.4121/7337b632-c7f5-4b6e-9d0e-820658e3cd4b.v1
The doi above is for this specific version of this dataset, 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: 10.4121/7337b632-c7f5-4b6e-9d0e-820658e3cd4b
Datacite citation style:
Balayn, Agathe (2023): Biased bird image dataset for the evaluation of explainability methods applied to computer vision (deep-learning-based) models. Version 1. 4TU.ResearchData. dataset. https://doi.org/10.4121/7337b632-c7f5-4b6e-9d0e-820658e3cd4b.v1
Other citation styles (APA, Harvard, MLA, Vancouver, Chicago, IEEE) available at Datacite
Dataset

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, representing 10 species of birds. The images were selected in order to inject class-specific biases in the dataset.

history
  • 2023-03-30 first online, published, posted
publisher
4TU.ResearchData
format
zipped file, containing images and saliency maps (.png, .jpg), their meta-data (.csv) such as predictions, and their annotations (.json)
organizations
TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, Department of Software Technology

DATA

files (2)