arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.06965cs.LGcs.CVcs.ROstat.ML
收藏

自动合成到真实综合

Automated Synthetic-to-Real Generalization

Texas A&M University(德克萨斯农工大学);NVIDIA(英伟达)

Wuyang Chen, Zhiding Yu, Zhangyang Wang, Anima Anandkumar

摘要:

在合成图像上训练的模型通常面临对真实数据的退化泛化。作为惯例,这些模型通常使用ImageNet预训练的表示进行初始化。然而,ImageNet知识的作用很少被讨论,尽管通常的做法是利用这些知识来保持泛化能力。一个例子是提前停止和逐层学习率的仔细手动调整,这被证明可以改善合成到真实的泛化,但也是费力和启发式的。在这项工作中,我们明确鼓励综合训练模型与ImageNet预训练模型保持相似的表示,并提出了一种\textit{learning-to-optimize (L2O)}策略来自动选择逐层学习率。我们证明了所提出的框架可以显着提高合成到真实的泛化性能,而无需查看和训练真实数据,同时也有利于下游任务,如领域自适应。代码可在:https://github.com/NVlabs/ASG.

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑