HyperAIHyperAI초신경
홈뉴스연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAIHyperAI초신경

Few Shot Semantic Segmentation On Coco 20I 2

평가 지표

Mean IoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Mean IoU
Paper TitleRepository
MSDNet (ResNet-101)76.4MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping
RePRI (ResNet-50)67.7Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?
MSDNet (ResNet-50)74.2MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototyping
FPTrans (DeiT-B/16)79.3Feature-Proxy Transformer for Few-Shot Segmentation
HSNet (HM, ResNet-50)69.7HM: Hybrid Masking for Few-Shot Segmentation
RPMM53.8Prototype Mixture Models for Few-shot Semantic Segmentation
HSNet (HM, ResNet-101)70.9HM: Hybrid Masking for Few-Shot Segmentation
FPTrans (ViT-B/16)76.9Feature-Proxy Transformer for Few-Shot Segmentation
DGPNet (ResNet-50)77.5Dense Gaussian Processes for Few-Shot Segmentation
VAT (HM, ResNet-50)69.7HM: Hybrid Masking for Few-Shot Segmentation
DGPNet (ResNet-101)78.5Dense Gaussian Processes for Few-Shot Segmentation
CWT (ResNet-50)66.5Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
0 of 12 row(s) selected.