HyperAIHyperAI초신경

Command Palette

Search for a command to run...

플랫폼

Image To Image Translation On Synthia To

평가 지표

mIoU (13 classes)

평가 결과

이 벤치마크에서 각 모델의 성능 결과

Paper Title
HRDA + PiPa74.8PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
MIC74.0MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
HRDA72.4HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
SePiCo71.4SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
CAMix (w DAFormer)69.2Context-Aware Mixup for Domain Adaptive Semantic Segmentation
DAFormer + ProCST68.2ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer
DAFormer67.4DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
TransDA-B66.3Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation
CPSL65.3Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation
ProDA+CRA63.7Cross-Region Domain Adaptation for Class-level Alignment
ProDA62.0Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
CAMix (w Deeplabv2 ResNet 101)59.7Context-Aware Mixup for Domain Adaptive Semantic Segmentation
IAST(ResNet-101)57.0Instance Adaptive Self-Training for Unsupervised Domain Adaptation
PyCDA (ResNet-101)53.3Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach
FADA (ResNet-101)52.5Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation
Bidirectional Learning (ResNet-101)51.4Bidirectional Learning for Domain Adaptation of Semantic Segmentation
DADA (ResNet-101)49.8DADA: Depth-aware Domain Adaptation in Semantic Segmentation
LRENT (DeepLabv2)48.7Confidence Regularized Self-Training
SWD48.1Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation
ADVENT48ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
0 of 28 row(s) selected.
Image To Image Translation On Synthia To | SOTA | HyperAI초신경