Beyond Sharing Weights for Deep Domain Adaptation
Beyond Sharing Weights for Deep Domain Adaptation
复制标题
DOI：
10.1109/tpami.2018.2814042
复制
发表时间：
2019-04-01
影响因子：
23.6
通讯作者：
Fua, Pascal
中科院分区：
文献类型：
--
作者：
Rozantsev, Artem;Salzmann, Mathieu;Fua, Pascal
在来自特定领域的数据上训练的分类器的性能在应用于相关但不同的领域时通常会下降。虽然从新域中注释许多示例可以解决这个问题，但它通常过于昂贵或不切实际。因此，域自适应已经成为这个问题的解决方案;它利用来自源域的注释数据，其中它是丰富的，以训练分类器在目标域中操作，其中它要么是稀疏的，甚至完全缺乏。在这种情况下，最近的趋势包括学习深度架构，其权重为两个域共享，这基本上相当于学习域不变特征。在这里，我们表明，它是更有效的明确建模从一个域到另一个域的转变。为此，我们引入了一个双流体系结构，其中一个在源域和目标域中的其他操作。与其他方法相比，对应层中的权重是相关的但不共享。我们证明，这在几个对象识别和检测任务上都比最先进的方法具有更高的准确性，并且在监督和无监督设置中始终优于具有共享权重的网络。
The performance of a classifier trained on data coming from a specific domain typically degrades when applied to a related but different one. While annotating many samples from the new domain would address this issue, it is often too expensive or impractical. Domain Adaptation has therefore emerged as a solution to this problem; It leverages annotated data from a source domain, in which it is abundant, to train a classifier to operate in a target domain, in which it is either sparse or even lacking altogether. In this context, the recent trend consists of learning deep architectures whose weights are shared for both domains, which essentially amounts to learning domain invariant features. Here, we show that it is more effective to explicitly model the shift from one domain to the other. To this end, we introduce a two-stream architecture, where one operates in the source domain and the other in the target domain. In contrast to other approaches, the weights in corresponding layers are related but not shared. We demonstrate that this both yields higher accuracy than state-of-the-art methods on several object recognition and detection tasks and consistently outperforms networks with shared weights in both supervised and unsupervised settings.