Shi-Yu Xia

model initialization (2) transfer learning (2) contrastive learning (1) continual learning (1) few-shot learning (1) gradient-based optimization (1) knowledge transfer (1) knowledge distillation (1) partial label learning (1) weight sharing (1) weight initialization (1) stage-wise weight sharing (1) variable-sized model (1) open-world detection (1) unknown class detection (1) open-world learning (1) knowledge inheritance (1) neural network (1) instance-dependent label noise (1) model compression (1)