ZEBRA: Explaining Rare Cases Through Outlying Interpretable Concepts

Pedro Madeira, André V. Carreiro, Alex Gaudio, Luís Rosado, Filipe Soares, Asim Smailagic

CVPRW 2023 pp. 3782-3788

doi:10.1109/CVPRW59228.2023.00392 /cvprw/2023/madeira2023cvprw-zebra/

Abstract

Anomaly detection methods can detect outliers, but what are the properties of an outlierƒ In this paper, we propose ZEBRA, a novel framework for generating explanations of an outlier based on the analysis of feature rarity in an interpretable feature space. The contributions of our work include: (a) a modular model-agnostic framework for explanations of outliers; (b) a statistical explanation method based on a rarity score and weighted aggregation functions; (c) multimodal explanations combining visual, textual, and numeric explanations. ZEBRA simplifies the mapping of low-level features to high-level concepts to generate multimodal and human-readable explanations of outliers.

CVPRW Semantic Scholar

Cite

Text

Madeira et al. "ZEBRA: Explaining Rare Cases Through Outlying Interpretable Concepts." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00392

Markdown

[Madeira et al. "ZEBRA: Explaining Rare Cases Through Outlying Interpretable Concepts." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/madeira2023cvprw-zebra/) doi:10.1109/CVPRW59228.2023.00392

BibTeX

@inproceedings{madeira2023cvprw-zebra,
  title     = {{ZEBRA: Explaining Rare Cases Through Outlying Interpretable Concepts}},
  author    = {Madeira, Pedro and Carreiro, André V. and Gaudio, Alex and Rosado, Luís and Soares, Filipe and Smailagic, Asim},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2023},
  pages     = {3782-3788},
  doi       = {10.1109/CVPRW59228.2023.00392},
  url       = {https://mlanthology.org/cvprw/2023/madeira2023cvprw-zebra/}
}