Codesota · Models · SeMask-LSHI Labs1 results · 1 benchmarks
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.

#BenchmarkArea · TaskMetricValueRankDateSource
01ADE20KVision & Documents · Semantic SegmentationmIoU49.4%#13/132026-04-20unverified
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 SeMask-L actually performs.

Vision & Documents
1
benchmark
avg rank #13.0
§ 05 · Related models

Other SHI Labs models scored on Codesota.

OneFormer (DiNAT-L)
Unknown params · 0 results
§ 06 · Sources & freshness

Where these numbers come from.

src
1
result
0 of 1 rows marked verified.