Chenxin Tao

self-supervised learning (4) representation learning (3) visual representation (3) transfer learning (2) vision-language model (2) dense prediction (2) siamese network (2) embedding learning (1) object detection (1) contrastive learning (1) autonomous driving (1) multi-modal learning (1) multimodal learning (1) efficient inference (1) image matching (1) attention mechanism (1) gradient descent (1) instruction tuning (1) neural network optimization (1) semantic alignment (1)