CDMAD addresses biased classifiers in SSL by refining pseudo-labels and class predictions, improving representation quality. Extensive experiments show CDMAD's effectiveness across various scenarios. It ensures Fisher consistency for balanced error.
In eine andere Sprache
aus dem Quellinhalt
arxiv.org
Wichtige Erkenntnisse aus
by Hyuck Lee,He... um arxiv.org 03-18-2024
https://arxiv.org/pdf/2403.10391.pdfTiefere Fragen