Model card
SegFormer-B5.
NVIDIA / NVlabsopen-sourceUnknown paramsHierarchical Mix Transformer (MiT-B5) + lightweight MLP decoder1 current SOTA
Seminal efficient transformer for semantic segmentation. MiT-B5 backbone with simple all-MLP decoder. 51.8 mIoU on ADE20K val. No positional encoding; produces multi-scale features. NeurIPS 2021.
§ 02 · Benchmarks
Every benchmark SegFormer-B5 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Cityscapes | Vision & Documents · Semantic Segmentation | miou | 84.0% | #1 | 2026-04-20 | source ↗ |
| 02 | ADE20K | Vision & Documents · Semantic Segmentation | mIoU | 51.8% | #12 | 2026-04-20 |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where SegFormer-B5 actually performs.
§ 06 · Sources & freshness
Where these numbers come from.
codesota-api
1
result
src
1
result
1 of 2 rows marked verified.