HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Few Shot Semantic Segmentation On Coco 20I 5

평가 지표

FB-IoU
Mean IoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
FB-IoU
Mean IoU
Paper TitleRepository
MIANet (VGG-16)73.8151.03MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation-
AENet (ResNet-50)78.557.1Eliminating Feature Ambiguity for Few-Shot Segmentation
HSNet (HM, ResNet-50)72.249.4HM: Hybrid Masking for Few-Shot Segmentation-
DACM (ResNet-50)71.648.1Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation
APANet (ResNet-50)-43APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation-
SCCAN (ResNet-50)74.253.9Self-Calibrated Cross Attention Network for Few-Shot Segmentation
IMR-HSNet (ResNet-50)-44.4Iterative Few-shot Semantic Segmentation from Image Label Text
DiffewS(SD2.1)-60.7Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
PGMA-Net (ResNet-50)76.757.1Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond-
DGPNet (ResNet-50)-56.2Dense Gaussian Processes for Few-Shot Segmentation
RePRI (ResNet-50)-41.6Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?
ProtoFormer (ResNet-50)73.353.4Prototype as Query for Few Shot Semantic Segmentation
FWB (ResNet-101)-23.65Feature Weighting and Boosting for Few-Shot Segmentation
FECANet (ResNet-50)71.147.6FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
VAT (ResNet-101)72.447.9Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
APANet (VGG-16)-43.2APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation-
RePRI (CECE-M,ResNet-50)-46.9Clustered-patch Element Connection for Few-shot Learning-
SSP (ResNet-101)-50.2Self-Support Few-Shot Semantic Segmentation
CWT (ResNet-50)-41.3Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
MCE (ResNet-50)-51.04Masked Cross-image Encoding for Few-shot Segmentation-
0 of 81 row(s) selected.