DIW Loss
Reported on 6 benchmarks across 2 tasks
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Robots3 results
- Heavy MR^-2· uses extra data28.37best: 56.9 (RepLoss)
- Reasonable MR^-2· uses extra data6.23best: 15.5 (TLL)
- Small MR^-2· uses extra data7.36best: 25.6 (FRCNN)
Computer Vision3 results
- Heavy MR^-2· uses extra data28.37best: 56.9 (RepLoss)
- Reasonable MR^-2· uses extra data6.23best: 15.5 (TLL)
- Small MR^-2· uses extra data7.36best: 25.6 (FRCNN)