Abstract | ||
---|---|---|
Active learning (AL) and semisupervised learning (SSL) are both promising solutions to hyperspectral image classification. Given a few initial labeled samples, this work combines AL and SSL in a novel manner, aiming to obtain more manually labeled and pseudolabeled samples and use them together with the initial labeled samples to improve the classification performance. First, based on a comparison... |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/TGRS.2016.2604290 | IEEE Transactions on Geoscience and Remote Sensing |
Keywords | Field | DocType |
Hyperspectral imaging,Training,Labeling,Sun,Support vector machines,Collaborative work | Data set,Semi-supervised learning,Computer science,Artificial intelligence,Random walker algorithm,Classifier (linguistics),Computer vision,Active learning,Pattern recognition,Segmentation,Support vector machine,Hyperspectral imaging,Machine learning | Journal |
Volume | Issue | ISSN |
55 | 1 | 0196-2892 |
Citations | PageRank | References |
14 | 0.49 | 31 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bin Sun | 1 | 14 | 0.49 |
Xudong Kang | 2 | 451 | 22.68 |
Shutao Li | 3 | 2594 | 139.10 |
Jon Atli Benediktsson | 4 | 4064 | 251.17 |