Few Shot Semantic Segmentation On Coco 20I 2 1
評価指標
mIoU
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | mIoU | Paper Title | Repository |
|---|---|---|---|
| MFNet (ResNet-50) | 24.1 | MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning | - |
| Label Anything (Vit-B/16-SAM) | 34.6 | Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts | |
| PPNet (ResNet-50) | 20.4 | Part-aware Prototype Network for Few-shot Semantic Segmentation | |
| Label Anything (ViT-B/16-MAE) | 31.9 | Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts | |
| DCAMA (Swin-B) | 31.7 | Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation | |
| PANet (ResNet-50) | 18.0 | PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment | - |
0 of 6 row(s) selected.