Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification

arXiv:2404.17173v1 Announce Type: new
Abstract: In semi-supervised learning, methods that rely on confidence learning to generate pseudo-labels have been widely proposed. However, increasing research finds that when faced with noisy and biased data, the model's representation network is more reliable than the classification network. Additionally, label generation methods based on model predictions often show poor adaptability across different datasets, necessitating customization of the classification network. Therefore, we propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model …

abstract arxiv beyond biased data classification confidence cs.ai cs.cv data dynamic embeddings generate hierarchical however labeling labels network representation research semi-supervised semi-supervised learning supervised learning type