Learning from error: A two-level combined model for image classification

We propose an error learning model for image classification. Motivated by the observation that classifiers trained using local grid regions of the images are often biased, i.e., contain many classification error, we present a two-level combined model to learn useful classification information from t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Mingyang Jiang, Chunxiao Li, Zirui Deng, Jufu Feng, Liwei Wang
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Accuracy Equations Hidden Markov models Machine learning Mathematical model Semantics Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!