论文标题
无监督域适应的周期标签一致网络
Cycle Label-Consistent Networks for Unsupervised Domain Adaptation
论文作者
论文摘要
域的适应性旨在利用标记的源域来学习具有不同分布的未标记目标域的分类器。先前的方法主要匹配两个域之间通过全局或类比对的分布。但是，全球一致性方法无法实现细粒度的班级重叠。伪标签监督的班级对准方法不能保证其可靠性。在本文中，我们通过利用分类标签的周期一致性，提出了一种简单而有效的域适应方法，即循环标签符合性网络（CLCN），该方法应用了双跨域的最接近的质心分类程序，以生成可靠的自我操纵性信号，以在目标域中歧视。循环标签一致的损失加强了源样本的地面真相标签和伪标签之间的一致性，从而导致源和目标域之间的统计上相似的潜在表示。几乎没有计算开销的任何现有分类网络，可以轻松地将这种新损失添加到任何现有的分类网络中。我们证明了方法对MNIST-USPS-SVHN，Office-31，Office-Home和Image Clef-Da基准的有效性。结果验证了所提出的方法可以减轻错误标记样本的负面影响并学习更多的判别特征，从而导致Office-31的绝对改善仅在Office-31上提高了9.4％，而Image Clef-DA的绝对改善则增加了6.3％。
Domain adaptation aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. Previous methods mostly match the distribution between two domains by global or class alignment. However, global alignment methods cannot achieve a fine-grained class-to-class overlap; class alignment methods supervised by pseudo-labels cannot guarantee their reliability. In this paper, we propose a simple yet efficient domain adaptation method, i.e. Cycle Label-Consistent Network (CLCN), by exploiting the cycle consistency of classification label, which applies dual cross-domain nearest centroid classification procedures to generate a reliable self-supervised signal for the discrimination in the target domain. The cycle label-consistent loss reinforces the consistency between ground-truth labels and pseudo-labels of source samples leading to statistically similar latent representations between source and target domains. This new loss can easily be added to any existing classification network with almost no computational overhead. We demonstrate the effectiveness of our approach on MNIST-USPS-SVHN, Office-31, Office-Home and Image CLEF-DA benchmarks. Results validate that the proposed method can alleviate the negative influence of falsely-labeled samples and learn more discriminative features, leading to the absolute improvement over source-only model by 9.4% on Office-31 and 6.3% on Image CLEF-DA.
