TY  - CONF
AU  - Adriana Romero
AU  - Carlo Gatta
AU  - Gustavo Camps-Valls
A2  - WHISPERS
PY  - 2014//
TI  - Unsupervised Deep Feature Extraction Of Hyperspectral Images
BT  - 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing
KW  - Convolutional networks
KW  - deep learning
KW  - sparse learning
KW  - feature extraction
KW  - hyperspectral image classification
N2  - This paper presents an effective unsupervised sparse feature learning algorithm to train deep convolutional networks on hyperspectral images. Deep convolutional hierarchical representations are learned and then used for pixel classification. Features in lower layers present less abstract representations of data, while higher layers represent more abstract and complex characteristics. We successfully illustrate the performance of the extracted representations in a challenging AVIRIS hyperspectral image classification problem, compared to standard dimensionality reduction methods like principal component analysis (PCA) and its kernel counterpart (kPCA). The proposed method largely outperforms the previous state-ofthe-art results on the same experimental setting. Results show that single layer networks can extract powerful discriminative features only when the receptive field accounts for neighboring pixels. Regarding the deep architecture, we can conclude that: (1) additional layers in a deep architecture significantly improve the performance w.r.t. single layer variants; (2) the max-pooling step in each layer is mandatory to achieve satisfactory results; and (3) the performance gain w.r.t. the number of layers is upper bounded, since the spatial resolution is reduced at each pooling, resulting in too spatially coarse output features.
L1  - http://refbase.cvc.uab.es/files/RGC2014.pdf
N1  - MILAB; LAMP; 600.079
ID  - Adriana Romero2014
ER  -