HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Few Shot Semantic Segmentation On Coco 20I

평가 지표

Mean IoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Mean IoU
Paper TitleRepository
FPTrans (DeiT-B/16)69.7Feature-Proxy Transformer for Few-Shot Segmentation
HSNet (HM, ResNet-50)65.2HM: Hybrid Masking for Few-Shot Segmentation-
DGPNet (ResNet-101)70.1Dense Gaussian Processes for Few-Shot Segmentation
HSNet (HM, ResNet-101)66.5HM: Hybrid Masking for Few-Shot Segmentation-
MSDNet (ResNet-101)73.9MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping
VAT (HM, ResNet-50)65.1HM: Hybrid Masking for Few-Shot Segmentation-
RPMM49.6Prototype Mixture Models for Few-shot Semantic Segmentation
CWT (ResNet-50)59.5Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
RePRI (ResNet-50)63.1Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?
VAT + MSI (ResNet101)69.2MSI: Maximize Support-Set Information for Few-Shot Segmentation
DGPNet (ResNet-50)68.9Dense Gaussian Processes for Few-Shot Segmentation
MSDNet (ResNet-50)72.1MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping
FPTrans (ViT-B/16)67.6Feature-Proxy Transformer for Few-Shot Segmentation
0 of 13 row(s) selected.