AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Automated Synthetic-to-Real Generalization

Wuyang Chen, Zhiding Yu, Zhangyang Wang, Animashree Anandkumar

ICML 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 10 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
Add ImageNet prediction-matching Proxy Guidance to large learning rates for all layers (ablation)ResNet-101 · VisDA-17 classificationTop-1 accuracy (%): 28.2 -> 58.7 (+30.5)Improved
Add ImageNet prediction-matching Proxy Guidance to small-backbone/large-FC learning rates (ablation)ResNet-101 · VisDA-17 classificationTop-1 accuracy (%): 49.3 -> 60.2 (+10.9)Improved
Increase Proxy Guidance strength from lambda 0.01 to 0.1 (ablation)ResNet-101 · VisDA-17 classificationAccuracy (%): 58.9 -> 60.1Improved
Increase Proxy Guidance strength from lambda 0.1 to 0.5 (ablation)ResNet-101 · VisDA-17 classificationAccuracy (%): 60.1 -> 58.5Hurt
Use Proxy Guidance instead of naive synthetic trainingFCN-Res50 · GTA5 → CityscapesmIoU (%): 23.29 -> 31.89Improved
Use Proxy Guidance instead of naive synthetic trainingFCN-VGG16 · GTA5 → CityscapesmIoU (%): 19.89 -> 31.47Improved
Initialize CRST (MRKLD) with the ASG source modelResNet-101 · VisDA-17 adaptationTop-1 accuracy (%): 77.9 (0.5) -> 84.6 (0.4)Improved
Use RL-L2O rather than hand-tuned learning-rate schedules (ablation)ASG · VisDA-17 classificationGeneralization accuracyImproved
Use Proxy Guidance rather than naively freezing the backbone (ablation)ResNet-101 · VisDA-17 classificationTop-1 accuracy (%): 53.3 -> 60.2Improved

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