Medical Image Segmentation On Bkai Igh
Metriken
Average Dice
mIoU
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Average Dice | mIoU | Paper Title | Repository |
|---|---|---|---|---|
| TGANet | 0.9023 | 0.8409 | TGANet: Text-guided attention for improved polyp segmentation | |
| ColonSegNet | 0.6881 | - | Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning | |
| QTSeg | - | - | QTSeg: A Query Token-Based Architecture for Efficient 2D Medical Image Segmentation | |
| BlazeNeo | 0.78802 | - | BlazeNeo: Blazing fast polyp segmentation and neoplasm detection | |
| FocalUNet | 0.8021 | - | Focal-UNet: UNet-like Focal Modulation for Medical Image Segmentation | |
| NeoUNet | 0.80723 | - | NeoUNet: Towards accurate colon polyp segmentation and neoplasm detection | - |
| EMCAD | 0.9296 | - | EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation | |
| TransResU-Net | 0.9154 | 0.8568 | TransResU-Net: Transformer based ResU-Net for Real-Time Colonoscopy Polyp Segmentation | |
| RaBiT | 0.94 | 0.886 | RaBiT: An Efficient Transformer using Bidirectional Feature Pyramid Network with Reverse Attention for Colon Polyp Segmentation |
0 of 9 row(s) selected.