Shu Kong

vision-language model (6) zero-shot learning (5) domain adaptation (4) semantic segmentation (4) depth estimation (3) foundation model (3) object detection (3) retrieval-augmented learning (2) metric learning (2) instance detection (2) 3d object detection (2) class imbalance (2) autonomous vehicle (2) camera pose (2) synthetic datum (2) model compression (2) multimodal learning (2) autonomous driving (2) video understanding (2) change detection (1)