Model card
SeMask-L.
SHI Labsopen-sourceUnknown paramsSwin-L encoder with Semantic Attention + Mask2Former decoder
Incorporates semantic information into the encoder via Semantic Attention at multiple stages. SeMask-L + Mask2Former achieves 49.35 mIoU on ADE20K val. ICCVW 2023.
§ 02 · Benchmarks
Every benchmark SeMask-L has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | ADE20K | Vision & Documents · Semantic Segmentation | mIoU | 49.4% | #13 | 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.
§ 05 · Related models
Other SHI Labs models scored on Codesota.
§ 06 · Sources & freshness
Where these numbers come from.
src
1
result
0 of 1 rows marked verified.