Unsupervised Domain Adaptation by Backpropagation
Unsupervised Domain Adaptation by Backpropagation
复制标题
DOI：
--
复制
发表时间：
2014-09
期刊：
影响因子：
--
通讯作者：
Yaroslav Ganin;V. Lempitsky
中科院分区：
文献类型：
--
作者：
Yaroslav Ganin;V. Lempitsky
性能最好的深度架构是在大量标记数据上训练的。在缺乏针对特定任务的标记数据的情况下，域自适应通常提供了一个有吸引力的选项，因为具有相似性质但来自不同域的标记数据（例如合成图像）是可用的。在这里，我们提出了一种在深度架构中进行域自适应的新方法，该方法可以在来自源域的大量标记数据和来自目标域的大量未标记数据（不需要标记的目标域数据）上进行训练。随着训练的进行，该方法促进了“深度”特征的出现，这些特征（i）对于源域上的主要学习任务是有区别的，并且（ii）对于域之间的移位是不变的。我们表明，这种适应行为可以在几乎任何前馈模型中实现，通过增加几个标准层和一个简单的新的梯度反转层。所得到的增强架构可以使用标准的反向传播来训练。总的来说，使用任何深度学习包都可以轻松实现该方法。该方法在一系列的图像分类实验中表现良好，在大的领域变化的情况下实现了自适应效果，并在Office数据集上优于以前的最先进的方法。
Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a different domain (e.g. synthetic images) are available. Here, we propose a new approach to domain adaptation in deep architectures that can be trained on large amount of labeled data from the source domain and large amount of unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of "deep" features that are (i) discriminative for the main learning task on the source domain and (ii) invariant with respect to the shift between the domains. We show that this adaptation behaviour can be achieved in almost any feed-forward model by augmenting it with few standard layers and a simple new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation. Overall, the approach can be implemented with little effort using any of the deep-learning packages. The method performs very well in a series of image classification experiments, achieving adaptation effect in the presence of big domain shifts and outperforming previous state-of-the-art on Office datasets.