HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Semantic Segmentation On Lip Val

Metrics

mIoU

Results

Performance results of various models on this benchmark

Model Name
mIoU
Paper TitleRepository
MuLA (ResNet-101)49.30%Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation-
HRNetV2 (HRNetV2-W48)55.90%High-Resolution Representations for Labeling Pixels and Regions
HRNetV2 + OCR + RMI (PaddleClas pretrained)58.2%Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
Attention+SSL (ResNet-101)44.73%Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing
Hulk(Finetune, ViT-B)63.98%Hulk: A Universal Knowledge Translator for Human-Centric Tasks
OCR (ResNet-101)55.6%Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
JPPNet (ResNet-101)51.37%Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark
UniHCP (finetune)63.86%UniHCP: A Unified Model for Human-Centric Perceptions
MMAN (ResNet-101)46.81%Macro-Micro Adversarial Network for Human Parsing
CE2P (ResNet-101)53.10%Devil in the Details: Towards Accurate Single and Multiple Human Parsing
OCR (HRNetV2-W48)56.65%Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
SOLIDER60.50%Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks
Hulk(Finetune, ViT-L)66.02%Hulk: A Universal Knowledge Translator for Human-Centric Tasks
0 of 13 row(s) selected.