Hyperspectral Image Classification on KSC (test)
99.85Average AccuracyDSCC
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| DSCC2026.04 | 99.85 | 99.83 | 99.81 | |
| S2Mamba2026.04 | 99.49 | 99.76 | 99.73 | |
| EASLPLabeled samples per class=102026.01 | 99.48 | 99.71 | 99.68 | |
| DEMAELabeled samples per class=102026.01 | 99.1 | 99.22 | 99.13 | |
| MambaHSI2026.04 | 98.54 | 99.02 | 98.91 | |
| SSEFN2026.04 | 98.34 | 99.04 | 98.93 | |
| DSTC2026.04 | 98.02 | 98.6 | 98.44 | |
| A2S2KLabeled samples per class=102026.01 | 97.92 | 98.04 | 97.81 | |
| CVSSN2026.04 | 97.91 | 98.52 | 98.35 | |
| CPModel Type=CP, Backbone=DenseNet121, Rank (R)=2, Number of trainable parameters=24k2026.05 | 97.6 | — | — | |
| DSXFormer2026.02 | 97.51 | 98.52 | 98.35 | |
| TuckerModel Type=Tucker, Backbone=DenseNet121, Rank (R)=2, Number of trainable parameters=24k2026.05 | 97.3 | — | — | |
| CTF-SSCLLabeled samples per class=102026.01 | 95.59 | 96.8 | 96.43 | |
| ScratchModel Type=Scratch, Backbone=DenseNet121, Rank (R)=2, Number of trainable parameters=553k2026.05 | 95.3 | — | — | |
| PyFormer2026.02 | 95.26 | 97.34 | 97.04 | |
| DMSGerLabeled samples per class=102026.01 | 95.12 | 94.7 | 94.11 | |
| SSTNLabeled samples per class=102026.01 | 94.61 | 96.46 | 96.04 | |
| PMCN2026.02 | 94.54 | 96.62 | 96.23 | |
| ReduceModel Type=Reduce, Backbone=DenseNet121, Rank (R)=2, Number of trainable parameters=24k2026.05 | 94.4 | — | — | |
| WaveFormer2026.02 | 93.97 | 96.03 | 95.58 | |
| RMAELabeled samples per class=102026.01 | 92.96 | 93.81 | 93.11 | |
| VIT2026.02 | 90.82 | 93.31 | 92.54 | |
| NL-GCNN2026.02 | 90.69 | 89.57 | 88.44 | |
| SwinT2026.02 | 90.56 | 93.12 | 92.33 | |
| SSSAN2026.04 | 89.3 | 93.13 | 92.35 | |
| MorphFormer2026.04 | 86.44 | 90.76 | 89.72 | |
| FADCNN2026.02 | 85.26 | 87.84 | 86.51 | |
| 2D CNN2026.02 | 84.31 | 84.72 | 83.02 | |
| SSTN2026.04 | 80.14 | 87.7 | 86.31 | |
| GCNN2026.02 | 78.92 | 85.56 | 83.82 | |
| SVM-RBF2026.02 | 72.26 | 78.53 | 76.04 | |
| CCF-2002026.02 | 69.86 | 83.81 | 81.83 |