Rethinking interpretation: Input-agnostic saliency mapping of deep visual classifiers

Saliency methods provide post-hoc model interpretation by attributing input features to the model outputs. Current methods mainly achieve this using a single input sample, thereby failing to answer input-independent inquiries about the model. We also show that input-specific saliency mapping is intr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Akhtar, Naveed, Jalwana, Mohammad A. A. K
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!