HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

Few Shot Semantic Segmentation On Coco 20I 5

评估指标

FB-IoU
Mean IoU

评测结果

各个模型在此基准测试上的表现结果

Paper Title
SegGPT (ViT)-67.9SegGPT: Segmenting Everything In Context
GF-SAM-66.8Bridge the Points: Graph-based Few-shot Segment Anything Semantically
PGMA-Net (ResNet-101)79.461.8Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond
DiffewS(SD2.1)-60.7Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
Matcher(DINOv2)-60.7Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
FPTrans (DeiT-B/16)-58.9Feature-Proxy Transformer for Few-Shot Segmentation
HMNet (ResNet-50)77.658.9Hybrid Mamba for Few-Shot Segmentation
DCAMA (Swin-B)76.958.3Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation
DGPNet (ResNet-101)-57.9Dense Gaussian Processes for Few-Shot Segmentation
AENet (ResNet-50)78.557.1Eliminating Feature Ambiguity for Few-Shot Segmentation
PGMA-Net (ResNet-50)76.757.1Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond
SCCAN (ResNet-101)74.857Self-Calibrated Cross Attention Network for Few-Shot Segmentation
MSANet (ResNet-101)56.856.3MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
DGPNet (ResNet-50)-56.2Dense Gaussian Processes for Few-Shot Segmentation
HDMNet (ResNet-50)77.756Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
MSDNet (ResNet-101)75.155.3MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping
ProtoFormer (ResNet-101)74.654.7Prototype as Query for Few Shot Semantic Segmentation
MSDNet (ResNet-50)74.554.5MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping
HMNet (VGG-16)75.554.5Hybrid Mamba for Few-Shot Segmentation
PFENet (SVF, ResNet-50)-54.38Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
0 of 81 row(s) selected.