Interpreting undesirable pixels for image classification on black-box models

Sin Han Kang, Hong Gyu Jung, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In an effort to interpret black-box models, researches for developing explanation methods have proceeded in recent years. Most studies have tried to identify input pixels that are crucial to the prediction of a classifier. While this approach is meaningful to analyse the characteristic of black-box models, it is also important to investigate pixels that interfere with the prediction. To tackle this issue, in this paper, we propose an explanation method that visualizes undesirable regions to classify an image as a target class. To be specific, we divide the concept of undesirable regions into two terms: (1) factors for a target class, which hinder that black-box models identify intrinsic characteristics of a target class and (2) factors for non-target classes that are important regions for an image to be classified as other classes. We visualize such undesirable regions on heatmaps to qualitatively validate the proposed method. Furthermore, we present an evaluation metric to provide quantitative results on ImageNet.

Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4250-4254
Number of pages5
ISBN (Electronic)9781728150239
DOIs
Publication statusPublished - 2019 Oct
Event17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of
Duration: 2019 Oct 272019 Oct 28

Publication series

NameProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Conference

Conference17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
CountryKorea, Republic of
CitySeoul
Period19/10/2719/10/28

Keywords

  • Explainable-AI
  • Interpretability

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Interpreting undesirable pixels for image classification on black-box models'. Together they form a unique fingerprint.

  • Cite this

    Kang, S. H., Jung, H. G., & Lee, S. W. (2019). Interpreting undesirable pixels for image classification on black-box models. In Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019 (pp. 4250-4254). [9022619] (Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2019.00523