Kang Li

vision-language model (3) knowledge distillation (2) image generation (2) domain adaptation (2) multimodal sentiment analysis (2) sound event detection (2) few-shot learning (1) semi-supervised learning (1) contrastive learning (1) transfer learning (1) spectral clustering (1) anomaly detection (1) text classification (1) model robustness (1) image segmentation (1) multimodal learning (1) text generation (1) domain generalization (1) sentiment classification (1) medical imaging (1)