Abstract | ||
---|---|---|
Active learning (AL) has obtained a great success in supervised remotely sensed hyperspectral image classification, since it is able to select highly informative training samples. As an intrinsically biased sampling approach, AL generally favors the selection of samples following discriminative distributions, which are located in low-density areas. However, hyperspectral data are often highly clas... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TGRS.2017.2747862 | IEEE Transactions on Geoscience and Remote Sensing |
Keywords | Field | DocType |
Training,Hyperspectral imaging,Error probability,Indexes,Feature extraction | Computer vision,Data set,Feature vector,Active learning,Pattern recognition,Computer science,Filter (signal processing),Sampling bias,Hyperspectral imaging,Feature extraction,Artificial intelligence,Discriminative model | Journal |
Volume | Issue | ISSN |
56 | 1 | 0196-2892 |
Citations | PageRank | References |
7 | 0.42 | 35 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chenying Liu | 1 | 39 | 2.94 |
Lin He | 2 | 53 | 4.12 |
Zhetao Li | 3 | 419 | 38.45 |
Jun Li | 4 | 1360 | 97.59 |