Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Task Learning on Cityscapes
Loading...
2.5
MR
Nash-MTL
2.21
4.1675
6.125
8.0825
Mar 8, 2026
MR
∆k%
Updated 2mo ago
Evaluation Results
Method
Method
Links
MR
∆k%
Nash-MTL
Cost=O(md)
2026.03
2.5
6.82
MoCo
Cost=O(md)
2026.03
3.75
9.9
MARIGOLD
Cost=O(d)
2026.03
4.5
8.62
IMTL-G
Cost=O(md)
2026.03
5
11.1
SDMGrad
Cost=O(md)
2026.03
5.25
7.79
CAGrad
Cost=O(md)
2026.03
7
11.64
FAMO
Cost=O(d)
2026.03
7
8.13
GradDrop
Cost=O(md)
2026.03
7.5
23.73
FAMO (rerun)
Cost=O(d)
2026.03
7.75
9.92
PCGrad
Cost=O(md)
2026.03
8.5
18.29
MGDA
Cost=O(md)
2026.03
9.5
44.14
MoDo
Cost=O(md)
2026.03
9.75
18.89
Feedback
Search any
task
Search any
task
