Semantic Segmentation on DeepGlobe
89.5mIoUOriginal Image
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Original Image2026.02 | 89.5 | — | — | — | — | |
| CompTokTokenizer Type=1D token-sequence2026.02 | 88.7 | 168.1 | 0.157 | 66 | — | |
| FlexTokTokenizer Type=1D token-sequence2026.02 | 86.7 | 154.8 | 0.154 | 63 | — | |
| TiTok-L-32Tokenizer Type=1D token-sequence2026.02 | 86.5 | 157 | 0.159 | 64 | — | |
| MAETokenizer Type=2D-grid2026.02 | 85.1 | 135.3 | 0.147 | 54 | — | |
| SemanticistTokenizer Type=1D token-sequence2026.02 | 84.2 | 159.9 | 0.144 | 64 | — | |
| VQGANTokenizer Type=2D-grid2026.02 | 83.4 | 162.9 | 0.149 | 54 | — | |
| SDXL VAETokenizer Type=2D-grid2026.02 | 79.7 | 145.9 | 0.131 | 48 | — | |
| RAETokenizer Type=2D-grid2026.02 | 75.9 | 146.1 | 0.13 | 47 | — | |
| DMTNet (TaP)Version=TaP, Shot count=15-shot2025.12 | 58.9 | — | — | — | — | |
| GF-SAMModel Category=generalist model, Shots=5-shot2024.10 | 57.7 | — | — | — | — | |
| DMTNet (TaP)Version=TaP, Shot count=10-shot2025.12 | 57.61 | — | — | — | — | |
| DMTNet (Decoder FT)Version=Decoder FT, Shot count=15-shot2025.12 | 55.3 | — | — | — | — | |
| DMTNet (Decoder FT)Version=Decoder FT, Shot count=10-shot2025.12 | 55.25 | — | — | — | — | |
| DMTNet (Vanilla)Version=Vanilla, Shot count=10-shot2025.12 | 54.78 | — | — | — | — | |
| DMTNet (Vanilla)Version=Vanilla, Shot count=15-shot2025.12 | 54.35 | — | — | — | — | |
| DMTNet (TaP)Version=TaP, Shot count=5-shot2025.12 | 54.18 | — | — | — | — | |
| MPAsource-training=false2026.02 | 53.1 | — | — | — | — | |
| DMTNet (Decoder FT)Version=Decoder FT, Shot count=5-shot2025.12 | 52.03 | — | — | — | — | |
| DMTNet (Vanilla)Version=Vanilla, Shot count=5-shot2025.12 | 51.76 | — | — | — | — | |
| DMTNet (TaP)Version=TaP, Shot count=3-shot2025.12 | 51.06 | — | — | — | — | |
| MatcherModel Category=generalist model, Shots=5-shot2024.10 | 50.9 | — | — | — | — | |
| DRAModel Category=specialist model, Shots=5-shot2024.10 | 50.1 | — | — | — | — | |
| DMTNet (Decoder FT)Version=Decoder FT, Shot count=3-shot2025.12 | 49.58 | — | — | — | — | |
| GF-SAMModel Category=generalist model, Shots=1-shot2024.10 | 49.5 | — | — | — | — | |
| DMTNet (Vanilla)Version=Vanilla, Shot count=3-shot2025.12 | 49.42 | — | — | — | — | |
| MatcherModel Category=generalist model, Shots=1-shot2024.10 | 48.1 | — | — | — | — | |
| TAVPSAM-based=true2026.02 | 46.1 | — | — | — | — | |
| DRAModel Category=specialist model, Shots=1-shot2024.10 | 41.3 | — | — | — | — | |
| APSegSAM-based=true2026.02 | 35.9 | — | — | — | — | |
| HSNetModel Category=specialist model, Shots=5-shot2024.10 | 35.1 | — | — | — | — | |
| PerSAM-FModel Category=generalist model, Shots=1-shot2024.10 | 35 | — | — | — | — | |
| PerSAMModel Category=generalist model, Shots=1-shot2024.10 | 31.4 | — | — | — | — | |
| PerSAMSAM-based=true2026.02 | 31.4 | — | — | — | — | |
| HSNetModel Category=specialist model, Shots=1-shot2024.10 | 29.7 | — | — | — | — |