NamedMask: Distilling Segmenters from Complementary Foundation Models
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)（2023）
关键词
accessible representation,category-agnostic salient object detector,category-specific archives,category-specific segmenters,CLIP archive labels,complementary foundation models,complementary strengths,data augmentation,DINO,image content,impressive semantic segmentation abilities,multiobject images,name regions,NamedMask,object names,object structure,pixel-level labels,refined masks,single-object images,standard segmentation architecture
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要