SOTAVerified

Synthetic-to-Real Translation

Synthetic-to-real translation is the task of domain adaptation from synthetic (or virtual) data to real data.

( Image credit: CYCADA )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 68 papers

TitleStatusHype
Transferring to Real-World Layouts: A Depth-aware Framework for Scene AdaptationCode1
Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene SegmentationCode0
Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic SegmentationCode1
MIC: Masked Image Consistency for Context-Enhanced Domain AdaptationCode2
ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDACode0
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic SegmentationCode1
Deliberated Domain Bridging for Domain Adaptive Semantic SegmentationCode1
G2L: A Global to Local Alignment Method for Unsupervised Domain Adaptive Semantic Segmentation—0
CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic SegmentationCode1
Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic SegmentationCode1
HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic SegmentationCode2
ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-TransferCode1
SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic SegmentationCode1
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic SegmentationCode1
Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic SegmentationCode1
Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic SegmentationCode1
Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation AdaptationCode1
TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain AugmentationCode0
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic SegmentationCode1
SPCL: A New Framework for Domain Adaptive Semantic Segmentation via Semantic Prototype-based Contrastive LearningCode1
Pixel-level Intra-domain Adaptation for Semantic Segmentation—0
Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency RegularizationCode0
Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer—0
Cross-Region Domain Adaptation for Class-level Alignment—0
Dual Path Learning for Domain Adaptation of Semantic SegmentationCode1
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.