Li Gu

few-shot learning (2) catastrophic forgetting (1) deep convolutional neural network (1) knowledge distillation (1) domain adaptation (1) uncertainty quantification (1) self-supervised learning (1) attention mechanism (1) mixture of expert (1) test-time adaptation (1) posterior distribution (1) differentiable programming (1) document analysis (1) convolutional neural network (1) semantic segmentation (1) parameter-efficient fine-tuning (1) generative adversarial network (1) stochastic gradient langevin dynamics (1) continual learning (1) model compression (1)