CoVar: Confidence-Variance-Guided Pseudo-Label Selection for Semi-Supervised Learning
Researchers have developed CoVar, a new framework for semi-supervised learning that improves pseudo-label selection by considering both confidence and variance. This method addresses the limitations of relying solely on confidence, which can be unreliable due to model overconfidence and class imbalance. CoVar jointly models maximum confidence and residual-class variance to assess the reliability of pseudo-labels, leading to improved performance on various segmentation and classification benchmarks. AI
IMPACT Enhances semi-supervised learning techniques by providing a more robust method for pseudo-label selection, potentially improving model performance with less labeled data.