Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Visual Planners for human Assistance on CrossTask (test)
Loading...
17.5
Success Rate (T=3)
PDPP
-0.7
4.025
8.75
13.475
Mar 26, 2023
Success Rate (T=3)
Mean Accuracy (T=3)
mIoU (T=3)
Success Rate (T=4)
Mean Accuracy (T=4)
mIoU (T=4)
Updated 3d ago
Evaluation Results
Method
Method
Links
Success Rate (T=3)
Mean Accuracy (T=3)
mIoU (T=3)
Success Rate (T=4)
Mean Accuracy (T=4)
mIoU (T=4)
PDPP
Protocol=protocol1
2023.03
17.5
48.5
55.3
9.8
44.3
56.6
PDPP
Protocol=protocol2
2023.03
11.6
36.7
47.7
6.3
35.1
50.9
VLaMP
Protocol=protocol1
2023.03
10.3
35.3
44
4.4
31.7
43.4
DDN
Protocol=protocol1
2023.03
6.8
25.8
35.2
3.6
24.1
37
Random w/goal
Protocol=protocol1
2023.03
0.3
13.4
23.6
0
12.7
27.8
Random
Protocol=protocol1
2023.03
0
0.9
1.5
0
0.9
1.9
Feedback
Search any
task
Search any
task