HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Semantic Segmentation On Densepass

Metriken

mIoU

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
Trans4PASS+ (multi-scale)57.23%Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation
Trans4PASS+ (single-scale)56.45%Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation
Trans4PASS (multi-scale)56.38%Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation
Trans4PASS (single-scale)55.25%Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation
DAFormer54.67%DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
PCS53.83%Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
P2PDA (Cityscapes+WildDash)48.52%Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation
SIM44.58%Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation
PoolFormer (MiT-B1)43.18%MetaFormer Is Actually What You Need for Vision
ECANet43.02%Capturing Omni-Range Context for Omnidirectional Segmentation
FAN (MiT-B1)42.54%Understanding The Robustness in Vision Transformers
SegFormer (MiT-B2)42.4%SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
ASMLP (MiT-B1)42.05%AS-MLP: An Axial Shifted MLP Architecture for Vision
P2PDA (Cityscapes)41.99%Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation
CycleMLP (MiT-B1)40.16%CycleMLP: A MLP-like Architecture for Dense Prediction
SegFormer (MiT-B1)38.5%SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
DPT (MiT-B1)36.50%DPT: Deformable Patch-based Transformer for Visual Recognition
SETR (PUP, Transformer-L)35.7%Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
SETR (MLA, Transformer-L)35.6%Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Seamless (Mapillary)34.14%Seamless Scene Segmentation
0 of 36 row(s) selected.
Semantic Segmentation On Densepass | SOTA | HyperAI