Model card
STU-Net-H.
Ziyan Huang et al.open-source1.4B paramsScalable U-Net1 current SOTA
Scalable and transferable U-Net. Huge variant (1.4B params). Pre-trained on TotalSegmentator.
§ 01 · Benchmarks
Every benchmark STU-Net-H has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | BTCV | Medical · Medical Image Segmentation | mean-dsc | 85.4% | #1 | 2023-04-13 | source ↗ |
| 02 | Synapse Multi-Organ CT | Medical · Medical Image Segmentation | mean-dsc | 84.9% | #4 | 2023-04-13 | source ↗ |
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 · Papers
1 paper with results for STU-Net-H.
- 2023-04-13· Medical· 2 results
STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-training
§ 04 · Related models
Other Ziyan Huang et al. models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
2
results
2 of 2 rows marked verified.