AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Real-to-Virtual Domain Unification for End-to-End Autonomous Driving

Luona Yang, Xiaodan Liang, Tairui Wang, Eric Xing

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 62 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
transform real images to virtual domain with DU-Drive(single) instead of fine-tuning on Carla dataPilotNet · Udacitysteering MAE: 6.053 -> 3.571Improved
transform real images to virtual domain with DU-Drive(single) instead of fine-tuning on TORCS dataPilotNet · Udacitysteering MAE: 5.808 -> 4.558Improved
transform real images to virtual domain with DU-Drive(single) instead of fine-tuning on TORCS dataPilotNet · Comma.aisteering MAE: 1.203 -> 1.061Improved
add joint training of prediction and transformation to conditional GAN (ablation)cGAN · Udacitysteering MAE: 5.921 -> 4.558Improved
train one predictor on both real datasets directly without domain unificationPilotNet · Comma.aisteering MAE: 1.208 -> 5.988Hurt
use unified model over two real domains instead of single-domain modelDU-Drive · Comma.aisteering MAE: 1.061 -> 1.079No clear effect
add domain unification with 20% labeled Udacity data (Carla)PilotNet · Udacity semi-supervisedsteering MAE: 7.86 -> 6.02Improved
add domain unification with 50% labeled Udacity data (Carla)PilotNet · Udacity semi-supervisedsteering MAE: 7.11 -> 5.15Improved
use unified instead of single model with 100% data (Carla)DU-Drive · Udacity semi-supervisedsteering MAE: 3.57 -> 3.81Hurt
use generated virtual images instead of real images (Carla, Udacity)input images · Udacityimage variance: 82745 -> 31650Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy