Single-source sound localization on VGGSound Instruments (test)
69.5IoU@0.3T-VSL
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| T-VSLMethod Category=Ours2024.04 | 69.5 | 64.6 | 51.4 | |
| AlignmentMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 65.8 | 60.4 | 48.7 | |
| AVGNMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 64.7 | 59.3 | 46.1 | |
| FNACMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 63.2 | 57.2 | 45.3 | |
| AudioCLIPMethod Category=CLIP-Based Baseline Methods, Pre-trained Encoders=AudioCLIP2024.04 | 62.7 | 58.3 | 45.2 | |
| MarginNCEMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 61.8 | 56.9 | 44.2 | |
| DSOLMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 61.6 | — | 43.7 | |
| Mix-and-LocalizeMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 59.3 | 53.8 | 41.5 | |
| EZ-VSLMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 58.8 | 52.3 | 39.9 | |
| LVSMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 57.9 | 51.5 | 39.4 | |
| CoarsetoFineMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 57.5 | 51.1 | 39.1 | |
| Wav2CLIPMethod Category=CLIP-Based Baseline Methods, Pre-trained Encoders=AudioCLIP2024.04 | 57.2 | 53.8 | 42 | |
| OTSMethod Category=Current SOTA Based Methods, Pre-trained Encoders=AudioCLIP2024.04 | 56.9 | 50.9 | 38.4 |