Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models

Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts. However, ad-hoc visual explanations of model decisions often reveal an alarming level of reliance on exploiting non-causal visual cues that strongly correlate...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-04
Hauptverfasser:	Wang, Dong, Yang, Yuewei, Tao, Chenyang, Gan, Zhe, Chen, Liqun, Kong, Fanjie, Henao, Ricardo, Lawrence, Carin
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Back propagation Back propagation networks Data integration Machine learning Medical imaging Representations Salience Visual signals
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!