Hyperspectral Image Classification Using Deep Pixel-Pair Features
Citations
2,095 citations
Cites methods from "Hyperspectral Image Classification ..."
...In [30], to allow a CNN to be appropriately trained using limited labeled data, the authors present a novel pixel-pair CNN to significantly augment the number of training samples....
[...]
1,105 citations
Cites background or methods from "Hyperspectral Image Classification ..."
...The SSRN has a deeper structure than those of 3-D CNNs used in [21]–[24], and contains shortcut...
[...]
...Multiple papers have demonstrated that CNNs can deliver the state-of-the-art results using spatialized input for HSI classification [21]–[23]....
[...]
...significant amount of labeled data for training [21]....
[...]
...feature extractor was proposed in [21], which can learn discriminative representations from pixel pairs and use a voting strategy to smooth final classification maps....
[...]
761 citations
629 citations
536 citations
Cites background from "Hyperspectral Image Classification ..."
..., Apache Spark, Caffe, Theano, Torch, and TensorFlow), which also find application in the hyperspectral analysis community [64], [65], [84], [337], [338]....
[...]
References
55,235 citations
49,914 citations
6,899 citations
3,607 citations
Additional excerpts
...very few training samples [27]....
[...]
2,071 citations
"Hyperspectral Image Classification ..." refers methods in this paper
...In [20], a deep learning architecture with multilayer stacked autoencoder was proposed to extract high-level features in an unsupervised manner using hyperspectral images....
[...]