0
喜欢
0
书签
声明论文
Learning to segment from a few well-selected training images   
摘  要:   We address the task of actively learning a segmentation system: given a large number of unsegmented images, and access to an oracle that can segment a given image, decide which images to provide, to quickly produce a segmenter (here, a discriminative random field) that is accurate over this distribution of images. We extend the standard models for active learner to define a system for this task that first selects the image whose expected label will reduce the uncertainty of the other unlabeled images the most, and then after greedily selects, from the pool of unsegmented images, the most informative image. The results of our experiments, over two real-world datasets (segmenting brain tumors within magnetic resonance images; and segmenting the sky in real images) show that training on very few informative images (here, as few as 2) can produce a segmenter that is as good as training on the entire dataset.
发  表:   International Conference on Machine Learning  2009

共享有6个版本
 [展开全部版本] 

Bibtex
创新指数 
阅读指数 
重现指数 
论文点评
还没有人点评哦

Feedback
Feedback
Feedback
我想反馈:
排行榜