HyperAIHyperAI超神経

Command Palette

Search for a command to run...

プラットフォーム

Unsupervised Domain Adaptation On Gtav To

評価指標

mIoU

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

Paper Title
MIC75.9MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
HRDA + PiPa75.6PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
CLUDA+HRDA74.4CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation
HRDA73.8HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
DAFormer + PiPa71.7PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
DIDA71.0Dual-level Interaction for Domain Adaptive Semantic Segmentation
SePiCo70.3SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
CAMix (w DAFormer)70.0Context-Aware Mixup for Domain Adaptive Semantic Segmentation
DAFormer + ProCST69.4ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer
DAFormer68.3DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
TransDA-B63.9Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation
BiSMAP (ResNet 101)61.2Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation
G2L59.7G2L: A Global to Local Alignment Method for Unsupervised Domain Adaptive Semantic Segmentation
FAFS58.8A Novel Unsupervised Domain Adaption Method for Depth-Guided Semantic Segmentation Using Coarse-to-Fine Alignment
Re-EnD-UDA57.98Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation
CAMix (w Deeplabv2 ResNet 101)55.2Context-Aware Mixup for Domain Adaptive Semantic Segmentation
Uncertainty + Adaboost50.9Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation
Uncertainty50.3Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
BiMaL47.3BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation
MRNet45.5Unsupervised Scene Adaptation with Memory Regularization in vivo
0 of 20 row(s) selected.