Zixuan Ye

image matting (4) semantic segmentation (3) alpha matte (2) feature extraction (1) similarity learning (1) style transfer (1) foreground extraction (1) video generation (1) weakly supervised learning (1) data augmentation (1) in-context learning (1) depth estimation (1) deep learning (1) saliency detection (1) vision-language model (1) diffusion model (1) reference image (1) text-to-image diffusion (1) dense prediction (1) object detection (1)