Remote Sensing Image-Text Retrieval on RSICD (test)
18.3Text Retrieval R@1MPS-CLIP
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| MPS-CLIPTraining Initialization=CLIP-based2026.01 | 18.3 | 37.42 | 50.32 | 13.28 | 37.04 | 54.73 | 35.18 | |
| HarMATraining Initialization=CLIP-based2026.01 | 16.36 | 34.48 | 47.74 | 12.92 | 37.17 | 53.07 | 33.62 | |
| PE-RSITRTraining Initialization=CLIP-based2026.01 | 14.13 | 31.51 | 44.78 | 11.63 | 33.92 | 50.73 | 31.12 | |
| Full-FT CLIPTraining Initialization=CLIP-based2026.01 | 13.54 | 30.83 | 43.46 | 11.55 | 33.14 | 49.83 | 30.39 | |
| UniAdapterTraining Initialization=CLIP-based2026.01 | 12.65 | 30.81 | 42.74 | 9.61 | 30.06 | 47.16 | 28.84 | |
| KAMCLTraining Initialization=Train from Scratch2026.01 | 11.99 | 27.17 | 38.33 | 7.78 | 25.23 | 40.02 | 25.08 | |
| PIR-ITRTraining Initialization=Train from Scratch2026.01 | 10.89 | 26.17 | 37.79 | 7.17 | 25.07 | 41.06 | 24.69 | |
| SingleLanguageTraining Initialization=CLIP-based2026.01 | 10.7 | 29.64 | 41.53 | 9.14 | 28.96 | 44.59 | 27.42 | |
| MSATraining Initialization=Train from Scratch2026.01 | 9.52 | 25.25 | 35.32 | 6.55 | 24.43 | 39.63 | 23.45 | |
| DOVETraining Initialization=Train from Scratch2026.01 | 8.66 | 22.35 | 34.95 | 6.04 | 23.95 | 40.35 | 22.72 | |
| Linear-probe CLIPTraining Initialization=CLIP-based2026.01 | 8.46 | 24.41 | 37.72 | 7.81 | 25.89 | 42.47 | 24.46 | |
| VGSGNTraining Initialization=Train from Scratch2026.01 | 8.33 | 21.87 | 32.57 | 6.53 | 23.13 | 36.85 | 21.55 | |
| CLIP-AdapterTraining Initialization=CLIP-based2026.01 | 7.11 | 19.48 | 31.01 | 7.67 | 24.87 | 39.73 | 21.65 | |
| SkyCLIPTraining Initialization=CLIP-based2026.01 | 6.59 | 16.1 | 26.53 | 7.14 | 22.34 | 34.29 | 18.83 |