Jaime Moraga
This article describes Jigsaw, a convolutional neural network (CNN) used in geosciences and based on Inception but tailored for geoscientific analyses. Introduces JigsawHSI (based on Jigsaw) and uses it on the land-use land-cover (LULC) classification problem with the Indian Pines, Pavia University and Salinas hyperspectral image data sets. The network is compared against HybridSN, a spectral-spatial 3D-CNN followed by 2D-CNN that achieves state-of-the-art results on the datasets. This short article proves that JigsawHSI is able to meet or exceed HybridSN's performance in all three cases. It also introduces a generalized Jigsaw architecture in d-dimensional space for any number of multimodal inputs. Additionally, the use of jigsaw in geosciences is highlighted, while the code and toolkit are made available.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Hyperspectral | Pavia University | Overall Accuracy | 100 | JigsawHSI |
| Hyperspectral | Indian Pines | Overall Accuracy | 99.74 | JigsawHSI |
| Hyperspectral | Salinas | OA@200 | 100 | JigsawHSI |
| Image Classification | Pavia University | Overall Accuracy | 100 | JigsawHSI |
| Image Classification | Indian Pines | Overall Accuracy | 99.74 | JigsawHSI |
| Image Classification | Salinas | OA@200 | 100 | JigsawHSI |
| Hyperspectral Image Segmentation | Pavia University | Overall Accuracy | 100 | JigsawHSI |
| Hyperspectral Image Segmentation | Indian Pines | Overall Accuracy | 99.74 | JigsawHSI |
| Hyperspectral Image Segmentation | Salinas | OA@200 | 100 | JigsawHSI |