Few-Shot Semantic Segmentation
Few-shot semantic segmentation (FSS) learns to segment target objects in query image given few pixel-wise annotated support image.
Papers
No papers found.
All datasetsPASCAL-5i (1-Shot)PASCAL-5i (5-Shot)COCO-20i (1-shot)COCO-20i (5-shot)FSS-1000 (1-shot)FSS-1000 (5-shot)COCO-20i -> Pascal VOC (1-shot)COCO-20i -> Pascal VOC (5-shot)COCO-20i (2-way 1-shot)COCO-20i (10-shot)PASCAL-5i (10-Shot)FSS-1000
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SegGPT (ViT) | Mean IoU | 83.2 | — | Unverified |
| 2 | PGMA-Net (ResNet-101) | Mean IoU | 77.6 | — | Unverified |
| 3 | DCAMA (ResNet-101) | FB-IoU | 77.6 | — | Unverified |
| 4 | PGMA-Net (ResNet-50) | Mean IoU | 74.1 | — | Unverified |
| 5 | PGMA-Net (ViT-B/16) | Mean IoU | 74.1 | — | Unverified |
| 6 | GF-SAM (DINOv2) | Mean IoU | 72.1 | — | Unverified |
| 7 | HMNet (ResNet-50) | Mean IoU | 70.4 | — | Unverified |
| 8 | AENet (ResNet-50) | Mean IoU | 70.3 | — | Unverified |
| 9 | HDMNet (DifFSS, ResNet-50) | Mean IoU | 70.2 | — | Unverified |
| 10 | VAT + MSI (ResNet-101) | Mean IoU | 70.1 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SegGPT (ViT) | Mean IoU | 89.8 | — | Unverified |
| 2 | GF-SAM (DINOv2) | Mean IoU | 82.6 | — | Unverified |
| 3 | PGMA-Net (ResNet-101) | Mean IoU | 78.6 | — | Unverified |
| 4 | FPTrans (DeiT-B/16) | Mean IoU | 78 | — | Unverified |
| 5 | DGPNet (ResNet-101) | Mean IoU | 75.4 | — | Unverified |
| 6 | PGMA-Net (ResNet-50) | Mean IoU | 75.2 | — | Unverified |
| 7 | DCAMA (Swin-B) | Mean IoU | 74.9 | — | Unverified |
| 8 | PGMA-Net (ViT-B/16) | Mean IoU | 74.6 | — | Unverified |
| 9 | AENet (ResNet-50) | Mean IoU | 74.2 | — | Unverified |
| 10 | HMNet (ResNet-50) | Mean IoU | 74.1 | — | Unverified |