论文标题
网络架构搜索域改编
Network Architecture Search for Domain Adaptation
论文作者
论文摘要
深网已被用来学习域适应性的可转移表示形式。现有的深层域适应方法系统地采用了专门为图像分类任务设计的流行手工制作的网络，从而导致次优域的适应性性能。在本文中，我们介绍了域名适应性（NASDA）的神经体系结构搜索，该域是一个原理框架，利用可区分的神经体系结构搜索来推导最佳的网络体系结构，以实现域的适应任务。 NASDA设计了两种新颖的培训策略：具有多内核最大平均差异的神经体系结构搜索，以得出最佳体系结构，以及功能生成器和一批分类器之间的对抗性训练，以合并功能生成器。我们通过实验证明，NASDA导致在几个领域适应基准的最新性能。
Deep networks have been used to learn transferable representations for domain adaptation. Existing deep domain adaptation methods systematically employ popular hand-crafted networks designed specifically for image-classification tasks, leading to sub-optimal domain adaptation performance. In this paper, we present Neural Architecture Search for Domain Adaptation (NASDA), a principle framework that leverages differentiable neural architecture search to derive the optimal network architecture for domain adaptation task. NASDA is designed with two novel training strategies: neural architecture search with multi-kernel Maximum Mean Discrepancy to derive the optimal architecture, and adversarial training between a feature generator and a batch of classifiers to consolidate the feature generator. We demonstrate experimentally that NASDA leads to state-of-the-art performance on several domain adaptation benchmarks.
