Codesota · Models · LightM-UNetLiao et al.1 results · 1 benchmarks
Model card

LightM-UNet.

Liao et al.open-source4M paramsLightweight Mamba + U-Net

Lightweight Mamba-assisted UNet. Very small model (4M params) with competitive performance.

§ 01 · Benchmarks

Every benchmark LightM-UNet has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01ACDCMedical · Medical Image Segmentationmean-dsc90.5%#3/62024-03-04source ↗
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.
§ 02 · Strengths by area

Where LightM-UNet actually performs.

Medical
1
benchmark
avg rank #3.0
§ 03 · Papers

1 paper with results for LightM-UNet.

  1. 2024-03-04· Medical· 1 result

    LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation

§ 04 · Related models

Other Liao et al. models scored on Codesota.

DBNet++ (ResNet-18) (1024)
Unknown params · 0 results
DBNet++ (ResNet-50) (1024)
Unknown params · 0 results
§ 05 · Sources & freshness

Where these numbers come from.

arxiv
1
result
1 of 1 rows marked verified.