特征重用的效用：数据匮乏环境下的迁移学习
The Utility of Feature Reuse: Transfer Learning in Data-Starved Regimes
AI总结：
该研究探讨了在目标样本少于100的数据匮乏环境下，迁移学习（特征重用与超参数化微调）对CNN图像分类器训练的有效性，并验证了其在分布外数据上的泛化性能。
摘要：
使用深度神经网络进行迁移学习，在将经过充分测试的计算机视觉系统部署到新领域（尤其是数据集有限的领域）方面已日益普及。我们描述了一个在数据匮乏环境下（目标样本少于100个）的迁移学习用例。我们评估了卷积特征提取和超参数化模型微调相对于目标训练数据规模的有效性，以及它们在协变量偏移（即分布外（OOD）数据）下的泛化性能。我们的实验表明，超参数化和特征重用都有助于在数据匮乏环境下成功应用迁移学习来训练图像分类器。我们提供了可视化解释来支持我们的发现，并得出结论：迁移学习增强了CNN架构在数据匮乏环境下的性能。
英文摘要：
The use of transfer learning with deep neural networks has increasingly become widespread for deploying well-tested computer vision systems to newer domains, especially those with limited datasets. We describe a transfer learning use case for a domain with a data-starved regime, having fewer than 100 labeled target samples. We evaluate the effectiveness of convolutional feature extraction and fine-tuning of overparameterized models with respect to the size of target training data, as well as their generalization performance on data with covariate shift, or out-of-distribution (OOD) data. Our experiments demonstrate that both overparameterization and feature reuse contribute to the successful application of transfer learning in training image classifiers in data-starved regimes. We provide visual explanations to support our findings and conclude that transfer learning enhances the performance of CNN architectures in data-starved regimes.
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。
