2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2015
DOI: 10.1109/igarss.2015.7326945
|View full text |Cite
|
Sign up to set email alerts
|

Deep supervised learning for hyperspectral data classification through convolutional neural networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

2
451
4
9

Year Published

2017
2017
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 818 publications
(466 citation statements)
references
References 9 publications
2
451
4
9
Order By: Relevance
“…SAE-LR was trained with 3300 epochs of pre-training and 400,000 epochs of fine-tuning [8]; the training time for fine-tuning was only 61.7 min. For a CNN [9], the training process of this model converged in almost 40 epochs, but in our experiments the model trained with 120 epochs achieved the best accuracy. The SSRN method needed 200 training epochs [13] and the FDSSC framework only needed 80 training epochs to achieve the best accuracy.…”
Section: Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…SAE-LR was trained with 3300 epochs of pre-training and 400,000 epochs of fine-tuning [8]; the training time for fine-tuning was only 61.7 min. For a CNN [9], the training process of this model converged in almost 40 epochs, but in our experiments the model trained with 120 epochs achieved the best accuracy. The SSRN method needed 200 training epochs [13] and the FDSSC framework only needed 80 training epochs to achieve the best accuracy.…”
Section: Resultsmentioning
confidence: 99%
“…In our experiment, we compared the proposed FDSSC framework to other deep-learning-based methods, that is, SAE-LR [8], CNN [9], 3D-CNN-LR [11], and the state-of-art SSRN method [13] (only for labeled pixels). SAE-LR was implemented with Theano [28].…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…In order to deal with this problem, DR methods are usually applied to reduce the spectral dimensionality prior to 2D-CNN being employed for feature extraction and classification [33][34][35]. For instance, in [33], the first three principal components (PCs) are extracted from HSI by PCA, and then a 2D-CNN is used to extract deep features from condensed HSI with a window size of 42 × 42 in order to predict the label of each pixel.…”
Section: D Convolution Operationmentioning
confidence: 99%
“…On the other hand, convnets require a 3D tensor as input and, accordingly, a patch-based labeling method was used in this study because it inherently aligns with CNNs. Using this approach, the multispectral image was decomposed into patches, which have both spectral and spatial information for a given pixel, and a class label is assigned to the center of each patch [40].…”
Section: Experiments Setupmentioning
confidence: 99%