Domain-Adversarial Training of Neural Networks
Domain-Adversarial Training of Neural Networks
复制标题
DOI：
10.1007/978-3-319-58347-1_10
复制
发表时间：
2017-01-01
期刊：
影响因子：
--
通讯作者：
Lempitsky, Victor
中科院分区：
文献类型：
--
作者：
Ganin, Yaroslav;Ustinova, Evgeniya;Lempitsky, Victor
我们引入了一种领域自适应的表示学习方法，其中训练和测试时的数据来自相似但不同的分布。我们的方法直接受到领域适应理论的启发，该理论认为，为了实现有效的领域转移，必须基于无法区分训练(源)和测试(目标)领域的特征进行预测。该方法在神经网络结构的环境中实现了这一思想，神经网络结构是在来自源域的标记数据和来自目标域的未标记数据(不需要标记的目标域数据)上训练的。随着训练的进行，该方法促进了以下特征的出现：(1)对源域上的主要学习任务具有区别性；(2)不分青红皂白地针对域之间的转换。我们表明，这种自适应行为可以在几乎任何前馈模型中实现，只需增加几个标准层和一个新的梯度反转层。所得到的增强的体系结构可以使用标准的反向传播进行训练，因此可以使用任何深度学习包轻松地实现。我们展示了我们的图像分类方法的成功，其中在标准基准上实现了最先进的领域自适应性能。在人的再识别应用中，我们还验证了描述符学习任务的有效性。
We introduce a representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains. The approach implements this idea in the context of neural network architectures that are trained on labeled data from the source domain and unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of features that are (i) discriminative for the main learning task on the source domain and (ii) indiscriminate with respect to the shift between the domains. We show that this adaptation behavior can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new Gradient Reversal Layer. The resulting augmented architecture can be trained using standard backpropagation, and can thus be implemented with little effort using any of the deep learning packages. We demonstrate the success of our approach for image classification, where state-of-the-art domain adaptation performance on standard benchmarks is achieved. We also validate the approach for descriptor learning task in the context of person re-identification application.