ICLRFeb, 2024
自导向掩蔽自编码器用于领域无关的自我监督学习
Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
Johnathan Xie, Yoonho Lee, Annie S. Chen, Chelsea Finn
TL;DRSelf-guided Masked Autoencoders (SMA) is a fully domain-agnostic masked modeling method for self-supervised learning, achieving state-of-the-art performance without domain-specific knowledge.