PFENet (SCL, ResNet-101)

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 LearningonCOCO-20i (5-shot)
Mean IoU· 2021-03-30
39.9
best: 67.9 (SegGPT (ViT))
Self-Guided and Cross-Guided Learning for Few-Shot Segmentation arXiv:2103.16129
Few-Shot LearningonCOCO-20i (1-shot)
Mean IoU· 2021-03-30
37
best: 59.4 (PGMA-Net (ResNet-101))
Self-Guided and Cross-Guided Learning for Few-Shot Segmentation arXiv:2103.16129
Meta-LearningonCOCO-20i (5-shot)
Mean IoU· 2021-03-30
39.9
best: 67.9 (SegGPT (ViT))
Self-Guided and Cross-Guided Learning for Few-Shot Segmentation arXiv:2103.16129
Meta-LearningonCOCO-20i (1-shot)
Mean IoU· 2021-03-30
37
best: 59.4 (PGMA-Net (ResNet-101))
Self-Guided and Cross-Guided Learning for Few-Shot Segmentation arXiv:2103.16129

Computer Vision2 results

Few-Shot Semantic SegmentationonCOCO-20i (5-shot)
Mean IoU· 2021-03-30
39.9
best: 67.9 (SegGPT (ViT))
Self-Guided and Cross-Guided Learning for Few-Shot Segmentation arXiv:2103.16129
Few-Shot Semantic SegmentationonCOCO-20i (1-shot)
Mean IoU· 2021-03-30
37
best: 59.4 (PGMA-Net (ResNet-101))
Self-Guided and Cross-Guided Learning for Few-Shot Segmentation arXiv:2103.16129