One-bit Supervision for Image Classification: Problem, Solution, and Beyond

This paper presents one-bit supervision, a novel setting of learning with fewer labels, for image classification. Instead of training model using the accurate label of each sample, our setting requires the model to interact with the system by predicting the class label of each sample and learn from...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-11
Hauptverfasser:	Hu, Hengtong, Xie, Lingxi, Xinyue Hue, Hong, Richang, Tian, Qi
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Annotations Computer Science - Computer Vision and Pattern Recognition Image annotation Image classification Labels Machine learning Self-supervised learning Semi-supervised learning Supervision
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!