论文标题
通过学习兼容表示形式来实现可重复使用的网络组件
Towards Reusable Network Components by Learning Compatible Representations
论文作者
论文摘要
本文提议迈出兼容的第一步，从而迈出可重复使用的网络组件。我们没有独立培训网络来独立培训网络，而是适应培训过程以生成跨任务兼容的网络组件。特别是，我们将网络分为两个组件，一个功能提取器和一个目标任务头，并提出了各种方法以实现它们之间的兼容性。我们系统地分析了标准数据集中图像分类任务的这些方法。我们证明我们可以生产直接兼容的组件，而无需对原始任务进行任何微调或损害精度。之后，我们演示了在三个应用程序上使用兼容组件的使用：无监督的域适应性，将分类器转移到具有不同架构的特征提取器之间，并提高了传输学习的计算效率。
This paper proposes to make a first step towards compatible and hence reusable network components. Rather than training networks for different tasks independently, we adapt the training process to produce network components that are compatible across tasks. In particular, we split a network into two components, a features extractor and a target task head, and propose various approaches to accomplish compatibility between them. We systematically analyse these approaches on the task of image classification on standard datasets. We demonstrate that we can produce components which are directly compatible without any fine-tuning or compromising accuracy on the original tasks. Afterwards, we demonstrate the use of compatible components on three applications: Unsupervised domain adaptation, transferring classifiers across feature extractors with different architectures, and increasing the computational efficiency of transfer learning.
