DISentangled Counterfactual Visual interpretER (DISCOVER) generalizes to natural images

We recently presented DISentangled COunterfactual Visual interpretER (DISCOVER), a method toward systematic visual interpretability of image-based classification models and demonstrated its applicability to two biomedical domains. Here we demonstrate that DISCOVER can be applied to the domain of nat...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Rotem, Oded, Zaritsky, Assaf
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 22.06.2024
Subjects
Image classification
Interpreters
Visual discrimination
Online AccessGet full text

Cover

More Information
Summary:We recently presented DISentangled COunterfactual Visual interpretER (DISCOVER), a method toward systematic visual interpretability of image-based classification models and demonstrated its applicability to two biomedical domains. Here we demonstrate that DISCOVER can be applied to the domain of natural images. First, DISCOVER visually interpreted the nose size, the muzzle area, and the face size as semantic discriminative visual traits discriminating between facial images of dogs versus cats. Second, DISCOVER visually interpreted the cheeks and jawline, eyebrows and hair, and the eyes, as discriminative facial characteristics. These successful visual interpretations across two natural images domains indicate that DISCOVER is a generalized interpretability method.
ISSN:2331-8422