Image Captioning on UCM Captions
79.92BLEU-4MF-RSVLM
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| MF-RSVLMCategory=Open-source Remote Sensing Vision-Language Models2025.12 | 79.92 | — | 88.51 | 89.47 | — | 387.9 | |
| SkyEyeGPTTotal Params=7B2025.12 | 78.4 | — | — | — | 90.7 | 2.368 | |
| Aware-Trans.Total Params=28M*2025.12 | 78.1 | — | — | — | 90.1 | 3.779 | |
| GeoMELTTotal Params=271M2025.12 | 77.2 | — | — | — | 89.8 | 3.917 | |
| HCNetTotal Params=25M*2025.12 | 74.5 | — | — | — | 88.3 | 3.518 | |
| BITATotal Params=3B2025.12 | 71.9 | — | — | — | 88.9 | 3.845 | |
| MC-NetTotal Params=138M*2025.12 | 67.9 | — | — | — | 84.5 | 3.355 | |
| Def. Trans.Total Params=90M*2025.12 | 67.9 | — | — | — | 82.3 | 3.463 | |
| MLCA-NETTotal Params=138M*2025.12 | 66.8 | — | — | — | 82.6 | 3.24 | |
| RSGPTTotal Params=13B2025.12 | 65.7 | — | — | — | 86.1 | 3.332 | |
| RS-CapRetTotal Params=7B2025.12 | 64.5 | — | — | — | 83.3 | 3.429 | |
| EarthDialCategory=Open-source Remote Sensing Vision-Language Models2025.12 | 59.77 | — | 32.43 | 44.08 | — | 127.7 | |
| VHMCategory=Open-source Remote Sensing Vision-Language Models2025.12 | 42.08 | — | 25.17 | 27.86 | — | 66.12 | |
| SkySenseGPTCategory=Open-source Remote Sensing Vision-Language Models2025.12 | 39.04 | — | 22.63 | 23.52 | — | 49.8 | |
| GPT-5Category=Closed-source Commercial Vision-Language Models2025.12 | 28.49 | — | 17.82 | 25.56 | — | 40.95 | |
| Qwen2.5-VLCategory=Open-source Vision-Language Models2025.12 | 27.87 | — | 17.23 | 21.48 | — | 35.36 | |
| MiniGPT-v2Category=Open-source Vision-Language Models2025.12 | 25.46 | — | 13.82 | 19.62 | — | 30.94 | |
| Claude-sonnet-4Category=Closed-source Commercial Vision-Language Models2025.12 | 20.12 | — | 13.35 | 20.99 | — | 30.04 | |
| Gemini-2.0Category=Closed-source Commercial Vision-Language Models2025.12 | 9.31 | — | 5.48 | 6.72 | — | 13.23 |