ملف الباحث
Meike Nauta
ورقة واحدة في مجموعة PaperMetrix
المنشورات
أوراق هذا المؤلف
-
Neural Prototype Trees for Interpretable Fine-grained Image Recognition
2021
Prototype-based methods use interpretable representations to address the black-box nature of deep learning models, in contrast to post-hoc explanation methods that only approximate such models. We propose the Neural Prototype Tree (ProtoTree), an intrinsically interpretable …