Visual Question Answering on EarthVQA (test)
79.26Overall AccuracyEarthVLNet
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| EarthVLNetSegmentation=true, Parameters=6.9B2026.01 | 79.26 | — | — | — | — | — | — | — | — | — | |
| SOBASegmentation=true, Parameters=19.9M2026.01 | 78.49 | — | — | — | — | — | — | — | — | — | |
| MCANSegmentation=true, Parameters=17.7M, Category=Classification-based2026.01 | 78.38 | — | — | — | — | — | — | — | — | — | |
| BUTDSegmentation=true, Parameters=12.3M, Category=Classification-based2026.01 | 78.25 | — | — | — | — | — | — | — | — | — | |
| LLaVANeXTSegmentation=false, Parameters=7.2B, Category=Generation-based2026.01 | 78.17 | — | — | — | — | — | — | — | — | — | |
| SOBAPrompt=true, Param (M)=40.46, FLOPs (B)=185.692023.12 | 78.14 | 89.63 | 82.64 | 80.17 | 67.86 | 61.4 | 49.3 | 0.7856 | 1.1457 | 0.8391 | |
| LXMERTSegmentation=true, Parameters=87.6M, Category=Classification-based2026.01 | 77.94 | — | — | — | — | — | — | — | — | — | |
| GoeChatSegmentation=false, Parameters=7.2B, Category=Generation-based2026.01 | 77.91 | — | — | — | — | — | — | — | — | — | |
| D-VQASegmentation=true, Parameters=17.6M, Category=Classification-based2026.01 | 77.8 | — | — | — | — | — | — | — | — | — | |
| BANSegmentation=true, Parameters=30.2M, Category=Classification-based2026.01 | 77.23 | — | — | — | — | — | — | — | — | — | |
| MCANPrompt=true, Param (M)=55.17, FLOPs (B)=200.392023.12 | 77.07 | 89.65 | 81.65 | 79.83 | 63.16 | 57.28 | 43.71 | 0.8169 | 1.2307 | 0.8793 | |
| BANPrompt=true, Param (M)=58.73, FLOPs (B)=185.152023.12 | 76.74 | 89.81 | 81.87 | 77.58 | 63.71 | 55.67 | 45.06 | 0.8197 | 1.2417 | 0.8835 | |
| D-VQAPrompt=true, Param (M)=37.79, FLOPs (B)=179.292023.12 | 76.59 | 89.73 | 82.12 | 77.38 | 63.99 | 55.14 | 43.2 | 0.9167 | 1.238 | 0.9627 | |
| SANSegmentation=false, Parameters=37.3M, Category=Classification-based2026.01 | 76.5 | — | — | — | — | — | — | — | — | — | |
| BUTDPrompt=true, Param (M)=34.95, FLOPs (B)=177.552023.12 | 76.49 | 90.01 | 82.02 | 77.16 | 60.95 | 56.29 | 42.29 | 0.8905 | 1.2925 | 0.9501 | |
| RSIVQASegmentation=false, Parameters=72.5M, Category=Classification-based2026.01 | 76.44 | — | — | — | — | — | — | — | — | — | |
| InstructBLIPSegmentation=false, Parameters=4.0B, Category=Generation-based2026.01 | 76.25 | — | — | — | — | — | — | — | — | — | |
| SANPrompt=false, Param (M)=32.30, FLOPs (B)=87.682023.12 | 75.66 | 87.59 | 81.79 | 76.26 | 59.23 | 55 | 43.25 | 1.1367 | 1.318 | 1.1609 | |
| Instruct-BLIPPrompt=false, Param (M)=≈4B, FLOPs (B)=N/A2023.12 | 75.25 | 89.67 | 79.69 | 76.96 | 63.34 | 59.72 | 45.68 | 0.7994 | 1.217 | 0.8627 | |
| ALBEFSegmentation=false, Parameters=290.6M, Category=Generation-based2026.01 | 74.8 | — | — | — | — | — | — | — | — | — | |
| BLIP-2Segmentation=false, Parameters=3.9B, Category=Generation-based2026.01 | 74.07 | — | — | — | — | — | — | — | — | — | |
| RSIVQAPrompt=false, Param (M)=41.41, FLOPs (B)=85.672023.12 | 73.71 | 85.32 | 80.44 | 75.01 | 56.63 | 51.55 | 39.25 | 1.7187 | 1.3468 | 1.6768 | |
| RSVQASegmentation=false, Parameters=34.9M, Category=Classification-based2026.01 | 73.67 | — | — | — | — | — | — | — | — | — | |
| MACSegmentation=false, Parameters=49.9M, Category=Classification-based2026.01 | 73.49 | — | — | — | — | — | — | — | — | — | |
| MACPrompt=false, Param (M)=38.64, FLOPs (B)=147.802023.12 | 71.98 | 82.89 | 79.46 | 72.53 | 55.86 | 46.32 | 40.5 | 1.4073 | 1.3375 | 1.3987 | |
| BLIP-2Prompt=false, Param (M)=≈4B, FLOPs (B)=N/A2023.12 | 71.07 | 88.13 | 81.92 | 70.26 | 58.58 | 42.72 | 28.34 | 1.879 | 1.32 | 1.8186 | |
| RSVQAPrompt=false, Param (M)=30.21, FLOPs (B)=86.582023.12 | 70.7 | 82.43 | 79.34 | 70.68 | 55.53 | 42.45 | 35.46 | 1.7336 | 1.3597 | 1.6914 |