Perception Over Time: Temporal Dynamics for Robust Image Understanding

While deep learning surpasses human-level performance in narrow and specific vision tasks, it is fragile and over-confident in classification. For example, minor transformations in perspective, illumination, or object deformation in the image space can result in drastically different labeling, which...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-03
Hauptverfasser:	Daniali, Maryam, Kim, Edward
Format:	Artikel
Sprache:	eng
Schlagworte:	Ablation Algorithms Computer vision Deep learning Human performance Machine learning Perturbation Robustness Visual perception
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!