Search Results for author: Duojun Huang

Found 4 papers, 3 papers with code

AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning

2 code implementations CVPR 2024 Duojun Huang, Xinyu Xiong, Jie Ma, Jichang Li, Zequn Jie, Lin Ma, Guanbin Li

In this paper, we propose a novel framework, termed AlignSAM, designed for automatic prompting for aligning SAM to an open context through reinforcement learning.

reinforcement-learning Reinforcement Learning +1

Annotation-Efficient Polyp Segmentation via Active Learning

no code implementations21 Mar 2024 Duojun Huang, Xinyu Xiong, De-Jun Fan, Feng Gao, Xiao-Jian Wu, Guanbin Li

To minimize annotation costs, we propose a deep active learning framework for annotation-efficient polyp segmentation.

Active Learning Segmentation

Divide and Adapt: Active Domain Adaptation via Customized Learning

1 code implementation CVPR 2023 Duojun Huang, Jichang Li, Weikai Chen, Junshi Huang, Zhenhua Chai, Guanbin Li

To accommodate active learning and domain adaption, the two naturally different tasks, in a collaborative framework, we advocate that a customized learning strategy for the target data is the key to the success of ADA solutions.

Active Learning Informativeness +3

Cannot find the paper you are looking for? You can Submit a new open access paper.