HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Domain Adaptation On Gta5 To Cityscapes

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

モデル名
mIoU
Paper TitleRepository
HRDA+PiPa75.6PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
DAFormer68.3DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
ProDA57.5Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
TransDA-B63.9Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation
FREDOM - Transformer73.6FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
ILM-ASSL76.1Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation
MIC75.9MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
FAFS58.8A Novel Unsupervised Domain Adaption Method for Depth-Guided Semantic Segmentation Using Coarse-to-Fine Alignment-
SePiCo70.3SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation-
HALO77.8Hyperbolic Active Learning for Semantic Segmentation under Domain Shift
ProDA+CRA58.6Cross-Region Domain Adaptation for Class-level Alignment-
FREDOM - DeepLabV261.3FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
DCF77.7Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation
GtA-SFDA (DeepLabv2-ResNet101)53.4Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation
DAFormer + ProCST69.4ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer
BiSMAP61.2Bidirectional 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-
MRNet48.3Unsupervised Scene Adaptation with Memory Regularization in vivo
EHTDI*62.0Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation
MRNet + Rectifying Label50.3Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation
0 of 26 row(s) selected.