Hyperspectral Image Classification With Convolutional Neural Network and Active Learning
Citations
582 citations
170 citations
Cites methods from "Hyperspectral Image Classification ..."
...In contrast, the active learning method based on posterior probability [98, 99, 100] is more widely used....
[...]
...[100] use convolutional neural networks to generate the posterior probability....
[...]
165 citations
159 citations
Cites background from "Hyperspectral Image Classification ..."
...…which is of great benefit to many potential applications such as image classification (Tuia et al., 2015; Han et al., 2018; Srivastava et al., 2019; Cao et al., 2020a), object and change detection (Zhang et al., 2018b, 2019b; Wu et al., 2019; Wu et al., 2020), mineral exploration (Gao et al.,…...
[...]
...Cao et al. (2020b) integrated CNNs and active learning to better utilize the unlabeled samples for hyperspectral image classification....
[...]
...[10] integrated CNNs and active learning to better utilize the unlabeled samples for hyperspectral image classification....
[...]
94 citations
References
30,843 citations
"Hyperspectral Image Classification ..." refers methods in this paper
...Also, the batch normalization (BN) [44] training strategy is used to help train the CNN....
[...]
17,184 citations
7,413 citations
6,122 citations
5,227 citations
"Hyperspectral Image Classification ..." refers methods in this paper
...A variety of heuristic AL strategies have been proposed in the machine learning field, such as uncertainty sampling [57], expected model change [58], variance reduction [59], estimated error reduction [60], and density-weighted methods [59]....
[...]