English

Automated Synthetic-to-Real Generalization

Machine Learning 2020-07-15 v1 Computer Vision and Pattern Recognition Robotics Machine Learning

Abstract

Models trained on synthetic images often face degraded generalization to real data. As a convention, these models are often initialized with ImageNet pre-trained representation. Yet the role of ImageNet knowledge is seldom discussed despite common practices that leverage this knowledge to maintain the generalization ability. An example is the careful hand-tuning of early stopping and layer-wise learning rates, which is shown to improve synthetic-to-real generalization but is also laborious and heuristic. In this work, we explicitly encourage the synthetically trained model to maintain similar representations with the ImageNet pre-trained model, and propose a \textit{learning-to-optimize (L2O)} strategy to automate the selection of layer-wise learning rates. We demonstrate that the proposed framework can significantly improve the synthetic-to-real generalization performance without seeing and training on real data, while also benefiting downstream tasks such as domain adaptation. Code is available at: https://github.com/NVlabs/ASG.

Keywords

Cite

@article{arxiv.2007.06965,
  title  = {Automated Synthetic-to-Real Generalization},
  author = {Wuyang Chen and Zhiding Yu and Zhangyang Wang and Anima Anandkumar},
  journal= {arXiv preprint arXiv:2007.06965},
  year   = {2020}
}

Comments

Accepted to ICML 2020

R2 v1 2026-06-23T17:06:23.605Z