DISentangled Counterfactual Visual interpretER (DISCOVER) 可泛化到自然图像
DISentangled Counterfactual Visual interpretER (DISCOVER) generalizes to natural images
AI总结：
本研究验证了解耦反事实视觉解释器DISCOVER可从生物医学领域泛化至自然图像领域，能识别猫狗区分及面部判别特征，证明其是通用的视觉可解释性方法。
摘要：
我们近期提出了DISentangled COunterfactual Visual interpretER（解耦反事实视觉解释器，简称DISCOVER），这是一种面向基于图像的分类模型系统性视觉可解释性的方法，且已验证其适用于两个生物医学领域。本文证明DISCOVER可应用于自然图像领域。首先，DISCOVER将鼻子大小、口鼻区域面积和脸部大小视觉解释为区分狗与猫面部图像的语义判别性视觉特征。其次，DISCOVER将脸颊与下颌线、眉毛与头发以及眼睛视觉解释为判别性面部特征。这些在两个自然图像领域的成功视觉解释表明，DISCOVER是一种具有泛化性的可解释性方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
