Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention

Interpretability is an important property for visual models as it helps researchers and users understand the internal mechanism of a complex model. However, generating semantic explanations about the learned representation is challenging without direct supervision to produce such explanations. We pr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-04
Hauptverfasser:	Yang, Yu, Kim, Seungbae, Joo, Jungseock
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Datasets Descriptions Labels Mapping Modular structures Neural networks Representations Semantics Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!