Revisiting Consistency Regularization for Semi-Supervised Learning

Consistency regularization is one of the most widely-used techniques for semi-supervised learning (SSL). Generally, the aim is to train a model that is invariant to various data augmentations. In this paper, we revisit this idea and find that enforcing invariance by decreasing distances between feat...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	International journal of computer vision 2023-03, Vol.131 (3), p.626-643
Hauptverfasser:	Fan, Yue, Kukleva, Anna, Dai, Dengxin, Schiele, Bernt
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial Intelligence Benchmarks Computer Imaging Computer Science Consistency Datasets Image Processing and Computer Vision Informatics Methods Pattern Recognition Pattern Recognition and Graphics Performance enhancement Regularization Semantics Semi-supervised learning Special Issue on Pattern Recognition (DAGM GCPR 2021) Vision
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!