Synthetic-to-Real Translation
55 papers with code • 4 benchmarks • 5 datasets
Synthetic-to-real translation is the task of domain adaptation from synthetic (or virtual) data to real data.
( Image credit: CYCADA )
Benchmarks
These leaderboards are used to track progress in Synthetic-to-Real Translation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Synthetic-to-Real Translation models and implementations
SYNTHIA
GTA5
Syn2Real
Sims4Action
WinSyn
Latest papers
DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
GaoLii/DSP
•
•
In addition, feature-level alignment is carried out by aligning the feature maps of the source and target images from student network using a weighted maximum mean discrepancy loss.
Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video Games
Recognizing Activities of Daily Living (ADL) is a vital process for intelligent assistive robots, but collecting large annotated datasets requires time-consuming temporal labeling and raises privacy concerns, e. g., if the data is collected in a real household.
PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training
lukemelas/pixmatch
•
•
CVPR 2021
In this work, we present a novel framework for unsupervised domain adaptation based on the notion of target-domain consistency training.
Self-supervised Augmentation Consistency for Adapting Semantic Segmentation
We propose an approach to domain adaptation for semantic segmentation that is both practical and highly accurate.
Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
However, such a supervision is not always available.
Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation
Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i. e., target domain.
MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation
cyang-cityu/MetaCorrection
•
•
CVPR 2021
Existing self-training based UDA approaches assign pseudo labels for target data and treat them as ground truth labels to fully leverage unlabeled target data for model adaptation.
Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
In this paper, we rely on representative prototypes, the feature centroids of classes, to address the two issues for unsupervised domain adaptation.
Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
kgl-prml/Pixel-Level-Cycle-Association
•
•
NeurIPS 2020
The conventional solution to this task is to minimize the discrepancy between source and target to enable effective knowledge transfer.
Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification
onuriel/PermutedAdaIN
•
•
CVPR 2021
In the setting of robustness, our method improves on both ImageNet-C and Cifar-100-C for multiple architectures.
