Codesota · Models · U-Mamba (Bot)Wang et al. (University of Toronto)2 results · 2 benchmarks
Model card

U-Mamba (Bot).

Wang et al. (University of Toronto)open-source59M paramsMamba (SSM) + U-Net

Mamba state space model for medical image segmentation with long-range dependency. Bot variant uses Mamba in bottleneck.

§ 01 · Benchmarks

Every benchmark U-Mamba (Bot) has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01Synapse Multi-Organ CTMedical · Medical Image Segmentationmean-dsc85.2%#3/112024-01-09source ↗
02ACDCMedical · Medical Image Segmentationmean-dsc90.3%#4/62024-01-09source ↗
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 U-Mamba (Bot) actually performs.

Medical
2
benchmarks
avg rank #3.5
§ 03 · Papers

1 paper with results for U-Mamba (Bot).

  1. 2024-01-09· Medical· 2 results

    U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

§ 05 · Sources & freshness

Where these numbers come from.

arxiv
2
results
2 of 2 rows marked verified.