Mistake detection on Multi-robot dataset Mutex (test)
76.83APTIMID
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| TIMIDEvaluation protocol=trained, Inf.Time (m)=0.022026.03 | 76.83 | 35.89 | 49.1 | |
| PEL4VADEvaluation protocol=trained, Inf.Time (m)=0.032026.03 | 64.43 | 35.2 | 45.53 | |
| Qwen 2.5 (ft)Evaluation protocol=fine-tuned, Inf.Time (m)=473.22026.03 | 41.48 | 24.41 | 30.73 | |
| Auto-EncoderEvaluation protocol=semi-supervised, Inf.Time (m)=0.632026.03 | 37.55 | 10.9 | 16.89 | |
| Qwen 2.5Evaluation protocol=zero-shot, Inf.Time (m)=423.62026.03 | 35.6 | 22.71 | 27.37 |