Dongheon Lee

model compression (1) representation learning (1) vision transformer (1) few-shot learning (1) domain generalization (1) model adaptation (1) efficient computing (1) image super-resolution (1) singular value decomposition (1) convolutional neural network (1) parameter-efficient fine-tuning (1) short-time fourier transform (1) domain shift (1) window attention (1) noise adaptation (1) real-time speech enhancement (1) spatial feature (1) self-attention emulation (1) multichannel speech enhancement (1) prototype perturbation (1)