合成画像から実画像への汎化を自動化する学習最適化手法
Automated Synthetic-to-Real Generalization
合成画像で学習したモデルがImageNet事前学習モデルの表現を維持するよう促し、層ごとの学習率選択を学習的最適化で自動化することで、実データなしで合成→実の汎化性能を向上させた研究。
著者: Wuyang Chen, Zhiding Yu, Zhangyang Wang, Anima Anandkumar
分類: cs.LG, cs.CV, cs.RO, stat.ML
原文アブストラクト
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.
