all AI news
Uncertainty-aware self-training with expectation maximization basis transformation
May 3, 2024, 4:58 a.m. | Zijia Wang, Wenbin Yang, Zhisong Liu, Zhen Jia
cs.CV updates on arXiv.org arxiv.org
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
More from arxiv.org / cs.CV updates on arXiv.org
Retrieval-Augmented Egocentric Video Captioning
2 days, 23 hours ago |
arxiv.org
Mirror-Aware Neural Humans
2 days, 23 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US