Image-to-Sound Retrieval on SoundingEarth 0.2m GSD (test)
0.434Recall@100GeoCLAP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP, Text Modality=true, Address Modality=true2023.09 | 0.434 | 159 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP, Text Modality=false, Address Modality=true2023.09 | 0.432 | 166 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP, Text Modality=true, Address Modality=false2023.09 | 0.423 | 172 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP, Text Modality=false, Address Modality=false2023.09 | 0.384 | 230 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP (frozen), Text Modality=false, Address Modality=false2023.09 | 0.352 | 360 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP (frozen), Text Modality=true, Address Modality=false2023.09 | 0.328 | 428 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP (frozen), Text Modality=true, Address Modality=true2023.09 | 0.317 | 439 | |
| GeoCLAPImage Encoder=SATMAE, Text-Audio Encoder=L-CLAP (frozen), Text Modality=false, Address Modality=true2023.09 | 0.298 | 546 | |
| BaselineImage Encoder=ResNet18, Text-Audio Encoder=ResNet18, Text Modality=false, Address Modality=false2023.09 | 0.256 | 814 |