Papers › Hyperspectral Image Classification of Convolutional Neural Network Combined with...

Hyperspectral Image Classification of Convolutional Neural Network Combined with Valuable Samples

1 Jun 2020Journal of Physics: Conference Series 2020 6archive 2025-07-28

Lixin Hu, Xiaobo Luo, Yufan Wei

Aiming at the problem that the manual labeling of samples in the hyperspectral image classification is expensive and laborious, a large number of unlabeled samples are not effectively utilized and the classification results are not ideal. A method which can provide valuable samples and employ convolutional neural network to extract spectral spatial features for classification is proposed. Active learning method is used to construct a valuable training sample set by iteratively selecting the most uncertain samples through support vector machine which performs well in small sample classification, and labeling them. Then the 3D convolutional neural network is used to extract the spectral spatial features of hyperspectral image. The experimental results of the hyperspectral classification on Indian Pines and PaviaU datasets show that the proposed method (3D VS-CNN) is better than traditional classification methods.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Active Learning Classification Few-Shot Image Classification Hyperspectral Image Classification Image Classification image-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Hyperspectral Image Classification	Indian Pines	3D VS-CNN	OA@15perclass	83.06±1.04	#5 of 34	Archive leaderboard	report
Hyperspectral Image Classification	Kennedy Space Center	3D VS-CNN	OA@15perclass	80.15±0.62	#11 of 14	Archive leaderboard	report
Hyperspectral Image Classification	Pavia University	3D VS-CNN	OA@15perclass	81.63±1.81	#8 of 33	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections