HyperAI초신경

Semi Supervised Semantic Segmentation On 27

평가 지표

Validation mIoU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Validation mIoU
Paper TitleRepository
CorrMatch (Deeplabv3+ with ResNet-101)76.4CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
UniMatch V2 (DINOv2-B)86.3UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
U2PL (DeepLab v3+ with ResNet-101)68.0Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
CPS (DeepLab v3+ with ResNet-101)64.1Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
UniMatch (ViT-B/16)77.9SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
CW-BASS (DeepLab v3+ with ResNet-50)72.8Confidence-Weighted Boundary-Aware Learning for Semi-Supervised Semantic Segmentation-
CPCL (DeepLab v3+ with ResNet-50)61.88Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
SemiVL (ViT-B/16)84.0SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
AllSpark76.07AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation
S4MC74.72Semi-Supervised Semantic Segmentation via Marginal Contextual Information
PrevMatch (ResNet-101)77.0Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
LogicDiag (DeepLab v3+ with ResNet-101)73.3Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation-
PrevMatch (ResNet-50)73.4Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
UniMatch (DeepLab v3+ with ResNet-101)75.20Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
0 of 14 row(s) selected.