Interpretable CNNs for Object Classification
This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part. Our method does not require additional annotations of object parts or...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 43(2021), 10 vom: 01. Okt., Seite 3416-3431
|
1. Verfasser: |
Zhang, Quanshi
(VerfasserIn) |
Weitere Verfasser: |
Wang, Xin,
Wu, Ying Nian,
Zhou, Huilin,
Zhu, Song-Chun |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2021
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S. |