HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Semi Supervised Semantic Segmentation On 28

평가 지표

Validation mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Validation mIoU
Paper TitleRepository
CPS (DeepLab v3+ with ResNet-101)67.4Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
CPCL (DeepLab v3+ with ResNet-50)67.02Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
UniMatch (ViT-B/16)80.1SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
PrevMatch (ResNet-101)78.5Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
SemiVL (ViT-B/16)85.6SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
PrevMatch (ResNet-50)75.4Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
AllSpark78.41AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation
CorrMatch (Deeplabv3+ with ResNet-101)78.5CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
UniMatch (DeepLab v3+ with ResNet-101)77.20Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
S4MC75.21Semi-Supervised Semantic Segmentation via Marginal Contextual Information
LogicDiag (DeepLab v3+ with ResNet-101)76.7Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation-
U2PL (DeepLab v3+ with ResNet-101)69.2Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
UniMatch V2 (DINOv2-B)87.9UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
0 of 13 row(s) selected.