IEEE

Label-Efficient Self-Supervised Learning for Sleep Stage Classification Using Multi-Channel In-Home EEG Data

Abstract: Automatic sleep stage classification is an important task to assist experts to perform diagnosis of sleep-related disorders. In supervised learning setting, the availability of a large ...

Apple Music Plans Transparency Tags for AI-Generated Tracks

Apple Music may add “Transparency Tags” for AI-made tracks. Opt-in metadata labels could shape discovery, trust, and rival ...

Apple Music Rolling Out Disclosure Tags for AI-Made Songs

Apple Music is rolling out a new metadata system called Transparency Tags, which indicates when AI has been used in the ...
IEEE

A Robust Deep Learning Framework for Mitigating Label Noise With Dual Selective Attention

Abstract: The performance of Machine Learning (ML) models is highly sensitive to data quality, still the impact of label accuracy remains underexplored. In this study, a novel architecture, the Dual ...
GitHub

Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning

Yaxin Hou, Bo Han, Yuheng Jia, Hui Liu, Junhui Hou, Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning, Advances in Neural Information ...