Audio-Visual Semantic Segmentation on AVSS (test)
37.4mIoUAV-Unified
Evaluation results
| Method | Links | ||
|---|---|---|---|
| AV-UnifiedTraining Mode=Joint2026.03 | 37.4 | 41.9 | |
| AVSeg2026.03 | 36.7 | 42 | |
| BAVS2026.03 | 32.6 | 36.4 | |
| TPAVI2026.03 | 29.8 | 35.2 |
| Method | Links | ||
|---|---|---|---|
| AV-UnifiedTraining Mode=Joint2026.03 | 37.4 | 41.9 | |
| AVSeg2026.03 | 36.7 | 42 | |
| BAVS2026.03 | 32.6 | 36.4 | |
| TPAVI2026.03 | 29.8 | 35.2 |