SiGCN (VGG-16)

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)
FB-IoU· 2023-01-09
73.5
best: 86.2 (PGMA-Net (ResNet-101))
Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network arXiv:2301.03194
Few-Shot LearningonPASCAL-5i (1-Shot)
Mean IoU· 2023-01-09
60.8
best: 83.2 (SegGPT (ViT))
Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network arXiv:2301.03194
Meta-LearningonPASCAL-5i (1-Shot)
FB-IoU· 2023-01-09
73.5
best: 86.2 (PGMA-Net (ResNet-101))
Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network arXiv:2301.03194
Meta-LearningonPASCAL-5i (1-Shot)
Mean IoU· 2023-01-09
60.8
best: 83.2 (SegGPT (ViT))
Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network arXiv:2301.03194

Computer Vision2 results

Few-Shot Semantic SegmentationonPASCAL-5i (1-Shot)
FB-IoU· 2023-01-09
73.5
best: 86.2 (PGMA-Net (ResNet-101))
Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network arXiv:2301.03194
Few-Shot Semantic SegmentationonPASCAL-5i (1-Shot)
Mean IoU· 2023-01-09
60.8
best: 83.2 (SegGPT (ViT))
Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network arXiv:2301.03194