Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/BAM (ResNet-50)

BAM (ResNet-50)

Reported on 18 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Methodology12 results

Few-Shot LearningonPASCAL-5i (1-Shot)
Mean IoU· 2022-03-15
67.81
best: 83.2 (SegGPT (ViT))
SOTA
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Meta-LearningonPASCAL-5i (1-Shot)
Mean IoU· 2022-03-15
67.81
best: 83.2 (SegGPT (ViT))
SOTA
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Few-Shot LearningonCOCO-20i (5-shot)
Mean IoU· 2022-03-15
51.16
best: 67.9 (SegGPT (ViT))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Few-Shot LearningonCOCO-20i (5-shot)
learnable parameters (million)· 2022-03-15
26.7
best: 47.7 (DCAMA (ResNet-101))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Few-Shot LearningonCOCO-20i (1-shot)
Mean IoU· 2022-03-15
46.23
best: 59.4 (PGMA-Net (ResNet-101))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Few-Shot LearningonCOCO-20i (1-shot)
learnable parameters (million)· 2022-03-15
26.7
best: 47.7 (DCAMA (ResNet-101))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Few-Shot LearningonPASCAL-5i (5-Shot)
Mean IoU· 2022-03-15
70.91
best: 89.8 (SegGPT (ViT))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Meta-LearningonCOCO-20i (5-shot)
Mean IoU· 2022-03-15
51.16
best: 67.9 (SegGPT (ViT))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Meta-LearningonCOCO-20i (5-shot)
learnable parameters (million)· 2022-03-15
26.7
best: 47.7 (DCAMA (ResNet-101))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Meta-LearningonCOCO-20i (1-shot)
Mean IoU· 2022-03-15
46.23
best: 59.4 (PGMA-Net (ResNet-101))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Meta-LearningonCOCO-20i (1-shot)
learnable parameters (million)· 2022-03-15
26.7
best: 47.7 (DCAMA (ResNet-101))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Meta-LearningonPASCAL-5i (5-Shot)
Mean IoU· 2022-03-15
70.91
best: 89.8 (SegGPT (ViT))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615

Computer Vision6 results

Few-Shot Semantic SegmentationonPASCAL-5i (1-Shot)
Mean IoU· 2022-03-15
67.81
best: 83.2 (SegGPT (ViT))
SOTA
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Few-Shot Semantic SegmentationonCOCO-20i (5-shot)
Mean IoU· 2022-03-15
51.16
best: 67.9 (SegGPT (ViT))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Few-Shot Semantic SegmentationonCOCO-20i (5-shot)
learnable parameters (million)· 2022-03-15
26.7
best: 47.7 (DCAMA (ResNet-101))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Few-Shot Semantic SegmentationonCOCO-20i (1-shot)
Mean IoU· 2022-03-15
46.23
best: 59.4 (PGMA-Net (ResNet-101))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Few-Shot Semantic SegmentationonCOCO-20i (1-shot)
learnable parameters (million)· 2022-03-15
26.7
best: 47.7 (DCAMA (ResNet-101))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615
Few-Shot Semantic SegmentationonPASCAL-5i (5-Shot)
Mean IoU· 2022-03-15
70.91
best: 89.8 (SegGPT (ViT))
Learning What Not to Segment: A New Perspective on Few-Shot Segmentation arXiv:2203.07615