Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This work was partly supported by the National Natural Science Foundation of China under Grant 12471498 and the Natural Science Foundation of Xiamen under Grant 3502Z202373042. (Corresponding author: Jialin Peng) J. Chen and S. Xiong are with College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China.J. Peng is with College of Computer Science and Technology, Huaqiao University, Xiamen 361021, China (e-mail: jialinpeng@hqu.edu.cn)
1
0
2
Forget expensive, fully-supervised EM segmentation: Prefer-DAS learns effectively from sparse prompts and local preferences, rivaling fully supervised performance while adapting to new domains.