Sound-to-Image Retrieval on SoundingEarth 10m GSD 1.0 (test)
44.7R@100GeoCLAP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP, Text=true, Address=true2023.09 | 44.7 | 144 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP, Text=true, Address=false2023.09 | 44.1 | 155 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP, Text=false, Address=true2023.09 | 44 | 156 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP, Text=false, Address=false2023.09 | 39.6 | 205 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP-frozen, Text=false, Address=false2023.09 | 38.1 | 271 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP-frozen, Text=true, Address=false2023.09 | 33.8 | 367 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP-frozen, Text=true, Address=true2023.09 | 33.1 | 320 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP-frozen, Text=false, Address=true2023.09 | 30.4 | 461 | |
| BaselineImage Encoder=ResNet18, Text-Audio Encoder=ResNet18, Text=false, Address=false2023.09 | 28.3 | 635 |