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 51–68 of 68 papers

TitleStatusHype
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic SegmentationCode0
MLSL: Multi-Level Self-Supervised Learning for Domain Adaptation with Spatially Independent and Semantically Consistent LabelingCode0
Confidence Regularized Self-TrainingCode1
Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial ApproachCode0
Bidirectional Learning for Domain Adaptation of Semantic SegmentationCode1
All about Structure: Adapting Structural Information across Domains for Boosting Semantic SegmentationCode0
Domain Adaptation for Structured Output via Discriminative Patch RepresentationsCode0
A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban ScenesCode1
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic SegmentationCode1
Domain Adaptation for Semantic Segmentation via Class-Balanced Self-TrainingCode0
Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain AdaptationCode0
Diverse Image-to-Image Translation via Disentangled RepresentationsCode1
Learning to Adapt Structured Output Space for Semantic SegmentationCode0
ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes—0
CyCADA: Cycle-Consistent Adversarial Domain AdaptationCode0
Curriculum Domain Adaptation for Semantic Segmentation of Urban ScenesCode0
Virtual to Real Reinforcement Learning for Autonomous DrivingCode0
FCNs in the Wild: Pixel-level Adversarial and Constraint-based AdaptationCode0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.