Paper ID: 2406.15918

DISentangled Counterfactual Visual interpretER (DISCOVER) generalizes to natural images

Oded Rotem, Assaf Zaritsky

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.

Submitted: Jun 22, 2024