HyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAI超神经

Image To Image Translation On Gtav To

评估指标

mIoU

评测结果

各个模型在此基准测试上的表现结果

模型名称
mIoU
Paper TitleRepository
CPSL60.8Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation
G2L59.7G2L: A Global to Local Alignment Method for Unsupervised Domain Adaptive Semantic Segmentation-
CAMix (w Deeplabv2 ResNet 101)55.2Context-Aware Mixup for Domain Adaptive Semantic Segmentation
CCM49.9Content-Consistent Matching for Domain Adaptive Semantic Segmentation
CAMix (w DAFormer)70.0Context-Aware Mixup for Domain Adaptive Semantic Segmentation
ADVENT44.8ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
DDB62.7Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation
CBST47.0Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
VGG16 60.341.3Very Deep Convolutional Networks for Large-Scale Image Recognition
SePiCo70.3SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation-
ProDA+CRA58.6Cross-Region Domain Adaptation for Class-level Alignment-
DAFormer + PiPa71.7PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
ResNet101 65.141.7Deep Residual Learning for Image Recognition
DAFormer + ProCST69.4ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer
EHTDI*62.0Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation
ProDA57.5Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
HRDA + PiPa75.6PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
Bidirectional Learning41.3Bidirectional Learning for Domain Adaptation of Semantic Segmentation
HRDA73.8HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
DAFormer68.3DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
0 of 22 row(s) selected.