KIT | KIT-Bibliothek | Impressum | Datenschutz

Explaining Convolutional Neural Networks by Tagging Filters

Nguyen, A. 1; Hagenmayer, D. 1; Weller, T.; Färber, M. ORCID iD icon 1
1 Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB), Karlsruher Institut für Technologie (KIT)

Abstract:

Convolutional neural networks (CNNs) have achieved astonishing performance on various image classification tasks, but it is difficult for humans to understand how a classification comes about. Recent literature proposes methods to explain the classification process to humans. These focus mostly on visualizing feature maps and filter weights, which are not very intuitive for non-experts in analyzing a CNN classification. In this paper, we propose FilTag, an approach to effectively explain CNNs even to non-experts. The idea is that when images of a class frequently activate a convolutional filter, then that filter is tagged with that class. These tags provide an explanation to a reference of a class-specific feature detected by the filter. Based on the tagging, individual image classifications can then be intuitively explained in terms of the tags of the filters that the input image activates. Finally, we show that the tags are helpful in analyzing classification errors caused by noisy input images and that the tags can be further processed by machines.


Volltext §
DOI: 10.5445/IR/1000155255
Veröffentlicht am 27.01.2023
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2021
Sprache Englisch
Identifikator KITopen-ID: 1000155255
Umfang 5 S.
Vorab online veröffentlicht am 20.09.2021
Nachgewiesen in arXiv
Dimensions
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page