Lechao Cheng

semantic segmentation (3) adversarial learning (3) vision-language model (3) 3d scene understanding (2) semi-supervised learning (2) semi-supervised object detection (2) instance segmentation (2) object detection (2) cross-modal alignment (2) weakly supervised learning (2) diffusion model (2) pseudo labeling (2) multi-instance learning (1) feature extraction (1) vision transformer (1) pose estimation (1) transfer learning (1) zero-shot learning (1) binary classification (1) video classification (1)