HyperAI
HyperAI
الرئيسية
المنصة
الوثائق
الأخبار
الأوراق البحثية
الدروس
مجموعات البيانات
الموسوعة
SOTA
نماذج LLM
لوحة الأداء GPU
الفعاليات
البحث
حول
شروط الخدمة
سياسة الخصوصية
العربية
HyperAI
HyperAI
Toggle Sidebar
البحث في الموقع...
⌘
K
Command Palette
Search for a command to run...
المنصة
الرئيسية
SOTA
التمييز_الدلالي_شبه_المشرف
Semi Supervised Semantic Segmentation On 28
Semi Supervised Semantic Segmentation On 28
المقاييس
Validation mIoU
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
Columns
اسم النموذج
Validation mIoU
Paper Title
UniMatch V2 (DINOv2-B)
87.9
UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
SemiVL (ViT-B/16)
85.6
SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
UniMatch (ViT-B/16)
80.1
SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance
PrevMatch (ResNet-101)
78.5
Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
CorrMatch (Deeplabv3+ with ResNet-101)
78.5
CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
AllSpark
78.41
AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation
UniMatch (DeepLab v3+ with ResNet-101)
77.20
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
LogicDiag (DeepLab v3+ with ResNet-101)
76.7
Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation
PrevMatch (ResNet-50)
75.4
Revisiting and Maximizing Temporal Knowledge in Semi-supervised Semantic Segmentation
S4MC
75.21
Semi-Supervised Semantic Segmentation via Marginal Contextual Information
U2PL (DeepLab v3+ with ResNet-101)
69.2
Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
CPS (DeepLab v3+ with ResNet-101)
67.4
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
CPCL (DeepLab v3+ with ResNet-50)
67.02
Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
0 of 13 row(s) selected.
Previous
Next