Yingjun Du

Latest

• ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion
• Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation
• EMO: Episodic Memory Optimization for Few-Shot Meta-Learning
• MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks
• SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail
• Hierarchical Variational Memory for Few-shot Learning Across Domains
• Variational Abnormal Behavior Detection with Motion Consistency
• Learning to Adapt with Memory for Probabilistic Few-Shot Learning
• Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation
• MetaNorm: Learning to Normalize Few-Shot Batches Across Domains
• Learning to Learn Variational Semantic Memory
• Learning to Learn with Variational Information Bottleneck for Domain Generalization
• Learning to Learn Kernels with Variational Random Features