Yangyang Shu

vision transformer (2) representation learning (1) zero-shot learning (1) semantic segmentation (1) few-shot learning (1) transfer learning (1) self-supervised learning (1) spiking neural network (1) pre-trained model (1) feature aggregation (1) few-shot semantic segmentation (1) multi-scale attention (1) spike-driven computing (1) energy-efficient computing (1) fine-grained visual recognition (1) neural network architecture (1) relationship descriptor (1)