Minimalistic fully convolution networks (MFCN): pixel-level classification for hyperspectral image with few labeled samples
Most of the existing deep learning methods for hyperspectral image (HSI) classification use pixel-wise or patch-wise classification. In this paper, we propose an image-wise classification method, where the network input is the original hyperspectral cube rather than the spectral curve of each pixel...
Saved in:
Published in | Optics express Vol. 30; no. 10; pp. 16585 - 16605 |
---|---|
Main Authors | , , , , |
Format | Journal Article |
Language | English |
Published |
09.05.2022
|
Online Access | Get full text |
Cover
Loading…
Summary: | Most of the existing deep learning methods for hyperspectral image (HSI) classification use pixel-wise or patch-wise classification. In this paper, we propose an image-wise classification method, where the network input is the original hyperspectral cube rather than the spectral curve of each pixel (i.e., pixel-wise) or neighbor region of each pixel (i.e., patch-wise). Specifically, we propose a minimalistic fully convolution network (MFCN) and a semi-supervised loss function, which can perform pixel-level classification for HSI with few labeled samples. The comparison experiments demonstrated the progress of our methods, using three new benchmark HSI datasets (WHU-Hi-LongKou, WHU-Hi-HanChuan and WHU-Hi-HongHu) with wavelength range from 400 to 1000nm. In the comparison experiments, we randomly selected 25 labeled pixels from each class for training, equivalent to only 0.11%, 0.16%, and 0.14% of all labeled pixels for the three datasets, respectively. In addition, through ablation studies and theoretical analysis, we verified and analyzed the effectiveness and superiority of our design choices. |
---|---|
Bibliography: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ISSN: | 1094-4087 1094-4087 |
DOI: | 10.1364/OE.453274 |