Text-to-Image Retrieval on RSITMD
1mRRemoteCLIP
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| RemoteCLIPZero-shot protocol=True, Distribution setting=In-distribution2025.12 | 1 | — | — | — | 48.97 | 1 | |
| VLM2GeoVecZero-shot protocol=True, Distribution setting=Out-of-distribution2025.12 | 2 | — | — | — | 41.03 | 2.5 | |
| GeoRSCLIPZero-shot protocol=True, Distribution setting=Out-of-distribution2025.12 | 3 | — | — | — | 38.3 | 2.7 | |
| VLM2VecZero-shot protocol=True, Distribution setting=Out-of-distribution2025.12 | 4 | — | — | — | 34.62 | 4.2 | |
| CLIPZero-shot protocol=True, Distribution setting=Out-of-distribution2025.12 | 5 | — | — | — | 35.22 | 5 | |
| SkyCLIPZero-shot protocol=True, Distribution setting=Out-of-distribution2025.12 | 6 | — | — | — | 32.21 | 5.7 | |
| LW-MCRYear=2021, Pre-train data=02026.04 | 13.55 | 3.84 | 14.96 | 25.73 | — | — | |
| AMFMNYear=2022, Pre-train data=0, Lat. (ms)=150.1, Thr. (q/s)=6.72026.04 | 15.51 | 4.92 | 17.83 | 28.33 | — | — | |
| KAMCLYear=2023, Pre-train data=02026.04 | 21.38 | 7.68 | 22.31 | 36.62 | — | — | |
| CLIP-BaseYear=2021, Pre-train data=400M, large-scale VLM pre-training=true, Lat. (ms)=12.0, Thr. (q/s)=83.32026.04 | 22.81 | 8.46 | 27.18 | 39.98 | — | — | |
| CLIP-BaselineTraining Dataset=-, Zero-Shot=true2025.12 | 23.86 | 0.0881 | 0.2785 | 0.4319 | — | — | |
| VSE++Training Dataset=RSITMD, Zero-Shot=false2025.12 | 24.54 | 0.0796 | 0.2487 | 0.3687 | — | — | |
| LW-MCRTraining Dataset=RSITMD, Zero-Shot=false2025.12 | 27.79 | 0.0779 | 0.3018 | 0.4978 | — | — | |
| AMFMNTraining Dataset=RSITMD, Zero-Shot=false2025.12 | 29.29 | 0.0996 | 0.3403 | 0.5296 | — | — | |
| GaLRTraining Dataset=RSITMD, Zero-Shot=false2025.12 | 31.41 | 0.1115 | 0.3668 | 0.5168 | — | — | |
| GaLRYear=2022, Pre-train data=0, Lat. (ms)=291.7, Thr. (q/s)=3.42026.04 | 31.41 | 14.82 | 31.64 | 42.48 | — | — | |
| SkyScriptYear=2024, Pre-train data=400M+2.6M, large-scale VLM pre-training=true, Lat. (ms)=13.5, Thr. (q/s)=74.12026.04 | 31.48 | 13.81 | 33.14 | 40.48 | — | — | |
| HVSATraining Dataset=RSITMD, Zero-Shot=false2025.12 | 33.15 | 0.1143 | 0.392 | 0.5745 | — | — | |
| SWANTraining Dataset=RSITMD, Zero-Shot=false2025.12 | 33.89 | 0.1124 | 0.4049 | 0.606 | — | — | |
| GeoRSCLIPTraining Dataset=RS5M, Zero-Shot=false2025.12 | 35.68 | 0.1416 | 0.4239 | 0.5752 | — | — | |
| FAAMIYear=2023, Pre-train data=02026.04 | 35.99 | 12.96 | 42.39 | 59.96 | — | — | |
| VGSGNYear=2024, Pre-train data=0, Lat. (ms)=106.5, Thr. (q/s)=9.42026.04 | 36.51 | 13.23 | 42.57 | 63.43 | — | — | |
| FAAMITraining Dataset=RSITMD, Zero-Shot=false2025.12 | 36.52 | 0.1296 | 0.4239 | 0.5995 | — | — | |
| PIRYear=2023, Pre-train data=0, Lat. (ms)=117.6, Thr. (q/s)=8.52026.04 | 38.24 | 12.17 | 41.68 | 63.41 | — | — | |
| PIRTraining Dataset=RSITMD, Zero-Shot=false2025.12 | 38.41 | 0.1277 | 0.4168 | 0.6341 | — | — | |
| MTGFEYear=2023, Pre-train data=02026.04 | 40.38 | 17.18 | 40.27 | 53.48 | — | — | |
| MTGFETraining Dataset=RSITMD, Zero-Shot=false2025.12 | 40.78 | 0.1659 | 0.485 | 0.6743 | — | — | |
| MultilanguageTraining Dataset=RSITMD, Zero-Shot=false2025.12 | 41.38 | 0.1761 | 0.4973 | 0.6659 | — | — | |
| ML RetrievalTraining Dataset=RSITMD, Backbone=ViT-B/322026.03 | 41.38 | 17.61 | 49.73 | 60.59 | — | — | |
| MSCMATYear=2024, Pre-train data=02026.04 | 41.38 | 15.18 | 47.35 | 64.73 | — | — | |
| TRSLLaVATraining Dataset=-, Zero-Shot=true2025.12 | 42.62 | 0.1826 | 0.4332 | 0.6841 | — | — | |
| SIPNYear=2025, Pre-train data=0, Lat. (ms)=120.3, Thr. (q/s)=8.32026.04 | 43.47 | 17.04 | 49.87 | 66.95 | — | — | |
| GRAFTYear=2024, Pre-train data=10.2M, large-scale VLM pre-training=true2026.04 | 44.61 | 24.92 | 53.39 | 61.47 | — | — | |
| PETLYear=2023, Pre-train data=400M, large-scale VLM pre-training=true2026.04 | 45.33 | 20.41 | 50.53 | 68.54 | — | — | |
| CLIPTraining Dataset=RET-3, Backbone=ViT-B/322026.03 | 47.63 | 22.61 | 55.27 | 69.87 | — | — | |
| IERRYear=2024, Pre-train data=02026.04 | 48.55 | 24.43 | 56.59 | 72.66 | — | — | |
| FTFYear=2026, Pre-train data=0, Candidate set size (K)=50, Lat. (ms)=24.7, Thr. (q/s)=40.62026.04 | 48.65 | 24.6 | 55.1 | 71.7 | — | — | |
| RemoteCLIPTraining Dataset=RET-3 + DET-10 + SEG-4, Backbone=ViT-B/322026.03 | 49.38 | 22.17 | 56.46 | 67.41 | — | — | |
| RemoteCLIPYear=2024, Pre-train data=400M+, large-scale VLM pre-training=true, Lat. (ms)=12.5, Thr. (q/s)=80.02026.04 | 49.38 | 22.17 | 56.46 | 73.41 | — | — | |
| EAPAYear=2025, Pre-train data=400M, large-scale VLM pre-training=true2026.04 | 49.91 | 24.16 | 57.48 | 71.81 | — | — | |
| GeoRSCLIPYear=2024, Pre-train data=400M+5M, large-scale VLM pre-training=true, Lat. (ms)=13.0, Thr. (q/s)=76.92026.04 | 50.1 | 23.54 | 57.52 | 74.6 | — | — | |
| FTFYear=2026, Pre-train data=0, Candidate set size (K)=100, Lat. (ms)=47.7, Thr. (q/s)=21.02026.04 | 50.49 | 26.7 | 57.8 | 72.34 | — | — | |
| FSSNYear=2025, Pre-train data=0, Lat. (ms)=128.7, Thr. (q/s)=7.82026.04 | 51.28 | 25.71 | 58.32 | 75.4 | — | — | |
| FTFYear=2026, Pre-train data=0, Candidate set size (K)=200, Lat. (ms)=93.7, Thr. (q/s)=10.72026.04 | 51.47 | 27.4 | 59 | 73.52 | — | — | |
| GeoRSCLIP-FTTraining Dataset=RSITMD + RSICD, Backbone=ViT-B/32, Evaluation Protocol=full fine-tuning2026.03 | 51.81 | 25.04 | 57.88 | 74.38 | — | — | |
| AVIONTraining Dataset=RSITMD + RSICD, Backbone=ViT-B/32, Evaluation Protocol=lightweight prompt learning2026.03 | 52.92 | 26.09 | 59.22 | 75.41 | — | — | |
| EBAKERYear=2024, Pre-train data=400M+0.2M, large-scale VLM pre-training=true, Lat. (ms)=13.6, Thr. (q/s)=73.92026.04 | 53.32 | 28.05 | 60.35 | 75.31 | — | — | |
| Geo-RSClip+RS5Mzero-shot=true2025.10 | — | — | — | — | 38.02 | — | |
| MaMMUT 400Mzero-shot=true, parameters=400M2025.10 | — | — | — | — | 32.7 | — | |
| PIR-ITRzero-shot=true2025.10 | — | — | — | — | 39.85 | — | |
| RS-MaMMut 400Mzero-shot=true, parameters=400M2025.10 | — | — | — | — | 42.58 | — | |
| RS-SigLIP2 400Mzero-shot=true, parameters=400M2025.10 | — | — | — | — | 47.26 | — | |
| SigLIP2 400Mzero-shot=true, parameters=400M2025.10 | — | — | — | — | 25.14 | — | |
| SkyScript SkyCLIP-30zero-shot=true2025.10 | — | — | — | — | 30.58 | — |