Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Semantic Segmentation on OctoSense day (test)
Loading...
41.1
mIoU
Late-fusion MAE
29.14
32.245
35.35
38.455
Jun 25, 2026
mIoU
Updated 29d ago
Evaluation Results
Method
Method
Links
mIoU
Late-fusion MAE
Fusion=late
2026.06
41.1
DINOv2
Encoder=DINOv2
2026.06
41
V-JEPA 2.1 (stereo)*
Encoder=V-JEPA 2.1, In...
2026.06
40.5
Late-fusion MAE (w/ full attention)
Attention=full
2026.06
40.5
Late-fusion MAE (w/o EV)
Removed Modality=EV
2026.06
40.3
V-JEPA 2.1
Encoder=V-JEPA 2.1
2026.06
40.2
Late-fusion MAE (w/o IMU)
Removed Modality=IMU
2026.06
40.2
Perception Enc.
Encoder=Perception Enc.
2026.06
38.8
DINOv3
Encoder=DINOv3
2026.06
38.2
Early-fusion MAE
Fusion=early
2026.06
37.9
SigLIP 2
Encoder=SigLIP 2
2026.06
37.7
Late-fusion MAE (w/o RGB)
Removed Modality=RGB
2026.06
36.6
Late-fusion MAE (w/o LiDAR)
Removed Modality=LiDAR
2026.06
35.1
RGB-only video MAE
Modality=RGB, Type=video
2026.06
32.7
Late-fusion MAE (w/ only RGB)
Modality=only RGB
2026.06
31
RGB-only image MAE
Modality=RGB, Type=image
2026.06
29.6
Feedback
Search any
task
Search any
task