HDMNet (DifFSS, ResNet-50)

Reported on 6 benchmarks across 3 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

Few-Shot LearningonPASCAL-5i (1-Shot)
Mean IoU· 2023-07-03
70.2
best: 83.2 (SegGPT (ViT))
DifFSS: Diffusion Model for Few-Shot Semantic Segmentation arXiv:2307.00773
Few-Shot LearningonCOCO-20i (1-shot)
Mean IoU· 2023-07-03
46.7
best: 59.4 (PGMA-Net (ResNet-101))
DifFSS: Diffusion Model for Few-Shot Semantic Segmentation arXiv:2307.00773
Meta-LearningonPASCAL-5i (1-Shot)
Mean IoU· 2023-07-03
70.2
best: 83.2 (SegGPT (ViT))
DifFSS: Diffusion Model for Few-Shot Semantic Segmentation arXiv:2307.00773
Meta-LearningonCOCO-20i (1-shot)
Mean IoU· 2023-07-03
46.7
best: 59.4 (PGMA-Net (ResNet-101))
DifFSS: Diffusion Model for Few-Shot Semantic Segmentation arXiv:2307.00773

Computer Vision2 results

Few-Shot Semantic SegmentationonPASCAL-5i (1-Shot)
Mean IoU· 2023-07-03
70.2
best: 83.2 (SegGPT (ViT))
DifFSS: Diffusion Model for Few-Shot Semantic Segmentation arXiv:2307.00773
Few-Shot Semantic SegmentationonCOCO-20i (1-shot)
Mean IoU· 2023-07-03
46.7
best: 59.4 (PGMA-Net (ResNet-101))
DifFSS: Diffusion Model for Few-Shot Semantic Segmentation arXiv:2307.00773