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/MSDNet (ResNet-50)

MSDNet (ResNet-50)

Reported on 42 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.

Methodology28 results

Few-Shot LearningonCOCO-20i (5-shot)
FB-IoU· 2024-09-17
74.5
best: 79.4 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonCOCO-20i (5-shot)
Mean IoU· 2024-09-17
54.5
best: 67.9 (SegGPT (ViT))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonCOCO-20i (5-shot)
learnable parameters (million)· 2024-09-17
1.5
best: 47.7 (DCAMA (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonCOCO-20i -> Pascal VOC (1-shot)
Mean IoU· 2024-09-17
72.1
best: 73.9 (MSDNet (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonPASCAL-5i (1-Shot)
FB-IoU· 2024-09-17
77.1
best: 86.2 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonPASCAL-5i (1-Shot)
Mean IoU· 2024-09-17
64.3
best: 83.2 (SegGPT (ViT))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonPASCAL-5i (1-Shot)
learnable parameters (million)· 2024-09-17
1.5
best: 31.5 (PPNet (ResNet-50))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonCOCO-20i (1-shot)
FB-IoU· 2024-09-17
70.4
best: 78.5 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonCOCO-20i (1-shot)
Mean IoU· 2024-09-17
46.5
best: 59.4 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonCOCO-20i (1-shot)
learnable parameters (million)· 2024-09-17
1.5
best: 47.7 (DCAMA (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonPASCAL-5i (5-Shot)
FB-IoU· 2024-09-17
82.1
best: 86.9 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonPASCAL-5i (5-Shot)
Mean IoU· 2024-09-17
68.7
best: 89.8 (SegGPT (ViT))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonPASCAL-5i (5-Shot)
learnable parameters (million)· 2024-09-17
1.5
best: 43 (FWB (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot LearningonCOCO-20i -> Pascal VOC (5-shot)
Mean IoU· 2024-09-17
74.2
best: 79.3 (FPTrans (DeiT-B/16))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonCOCO-20i (5-shot)
FB-IoU· 2024-09-17
74.5
best: 79.4 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonCOCO-20i (5-shot)
Mean IoU· 2024-09-17
54.5
best: 67.9 (SegGPT (ViT))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonCOCO-20i (5-shot)
learnable parameters (million)· 2024-09-17
1.5
best: 47.7 (DCAMA (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonCOCO-20i -> Pascal VOC (1-shot)
Mean IoU· 2024-09-17
72.1
best: 73.9 (MSDNet (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonPASCAL-5i (1-Shot)
FB-IoU· 2024-09-17
77.1
best: 86.2 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonPASCAL-5i (1-Shot)
Mean IoU· 2024-09-17
64.3
best: 83.2 (SegGPT (ViT))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonPASCAL-5i (1-Shot)
learnable parameters (million)· 2024-09-17
1.5
best: 31.5 (PPNet (ResNet-50))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonCOCO-20i (1-shot)
FB-IoU· 2024-09-17
70.4
best: 78.5 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonCOCO-20i (1-shot)
Mean IoU· 2024-09-17
46.5
best: 59.4 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonCOCO-20i (1-shot)
learnable parameters (million)· 2024-09-17
1.5
best: 47.7 (DCAMA (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonPASCAL-5i (5-Shot)
FB-IoU· 2024-09-17
82.1
best: 86.9 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonPASCAL-5i (5-Shot)
Mean IoU· 2024-09-17
68.7
best: 89.8 (SegGPT (ViT))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonPASCAL-5i (5-Shot)
learnable parameters (million)· 2024-09-17
1.5
best: 43 (FWB (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Meta-LearningonCOCO-20i -> Pascal VOC (5-shot)
Mean IoU· 2024-09-17
74.2
best: 79.3 (FPTrans (DeiT-B/16))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316

Computer Vision14 results

Few-Shot Semantic SegmentationonCOCO-20i (5-shot)
FB-IoU· 2024-09-17
74.5
best: 79.4 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonCOCO-20i (5-shot)
Mean IoU· 2024-09-17
54.5
best: 67.9 (SegGPT (ViT))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonCOCO-20i (5-shot)
learnable parameters (million)· 2024-09-17
1.5
best: 47.7 (DCAMA (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonCOCO-20i -> Pascal VOC (1-shot)
Mean IoU· 2024-09-17
72.1
best: 73.9 (MSDNet (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonPASCAL-5i (1-Shot)
FB-IoU· 2024-09-17
77.1
best: 86.2 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonPASCAL-5i (1-Shot)
Mean IoU· 2024-09-17
64.3
best: 83.2 (SegGPT (ViT))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonPASCAL-5i (1-Shot)
learnable parameters (million)· 2024-09-17
1.5
best: 31.5 (PPNet (ResNet-50))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonCOCO-20i (1-shot)
FB-IoU· 2024-09-17
70.4
best: 78.5 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonCOCO-20i (1-shot)
Mean IoU· 2024-09-17
46.5
best: 59.4 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonCOCO-20i (1-shot)
learnable parameters (million)· 2024-09-17
1.5
best: 47.7 (DCAMA (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonPASCAL-5i (5-Shot)
FB-IoU· 2024-09-17
82.1
best: 86.9 (PGMA-Net (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonPASCAL-5i (5-Shot)
Mean IoU· 2024-09-17
68.7
best: 89.8 (SegGPT (ViT))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonPASCAL-5i (5-Shot)
learnable parameters (million)· 2024-09-17
1.5
best: 43 (FWB (ResNet-101))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316
Few-Shot Semantic SegmentationonCOCO-20i -> Pascal VOC (5-shot)
Mean IoU· 2024-09-17
74.2
best: 79.3 (FPTrans (DeiT-B/16))
MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping arXiv:2409.11316