Uncertainty-aware self-training with expectation maximization basis transformation

arXiv:2405.01175v1 Announce Type: new
Abstract: Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confidence issue brought by the hard labels, even some confidence-related regularizers cannot comprehensively catch the uncertainty. Therefore, we propose a new self-training framework to combine uncertainty information of both model and dataset. Specifically, we propose to use Expectation-Maximization (EM) to smooth the labels and comprehensively estimate the uncertainty information. We …

abstract algorithms arxiv confidence cs.ai cs.cv deep learning framework however issue key labels modeling process self-training the key training transformation type uncertainty