ML Research Wiki / Benchmarks / Multi-Task Learning / NYUv2

NYUv2

Multi-Task Learning Benchmark

Performance Over Time

📊 Showing 2 results | 📏 Metric: Mean IoU

Click "Edit" next to any result to modify it, or add a new result at the bottom. All changes will be reviewed before going live.

Yellow rows = Pending edits Green rows = Pending new results

Model	Paper	Mean IoU	Date	Actions
SwinMTL	SwinMTL: A Shared Architecture for Simultaneous D…	58.14	2024-03-15
Nash-MTL	Multi-Task Learning as a Bargaining Game	40.13	2022-02-02

Rank	Model	Paper	Mean IoU	Date	Code
1	SwinMTL	SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images	58.14	2024-03-15	📦 pardistaghavi/swinmtl
2	Nash-MTL	Multi-Task Learning as a Bargaining Game	40.13	2022-02-02	📦 torchjd/torchjd 📦 avivnavon/nash-mtl 📦 cranial-xix/famo 📦 autumn9999/go4align

2024

SwinMTL

pardistaghavi/swinmtl

2022

Nash-MTL

torchjd/torchjd avivnavon/nash-mtl