当前位置: X-MOL 学术Neurocomputing › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Cycle Label-Consistent Networks for Unsupervised Domain Adaptation
Neurocomputing ( IF 5.5 ) Pub Date : 2021-01-01 , DOI: 10.1016/j.neucom.2020.07.124
Mei Wang , Weihong Deng

Abstract 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.

中文翻译:

用于无监督域适应的循环标签一致网络

Abstract 域适应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。以前的方法主要通过全局或类对齐来匹配两个域之间的分布。然而,全局对齐方法无法实现细粒度的类到类重叠;由伪标签监督的类对齐方法不能保证其可靠性。在本文中,我们提出了一种简单而有效的域适应方法,即循环标签一致网络(CLCN),利用分类标签的循环一致性,它应用双跨域最近质心分类程序来生成可靠的自监督信号用于目标域中的区分。循环标签一致性损失加强了源样本的真实标签和伪标签之间的一致性,导致源域和目标域之间的潜在表示在统计上相似。这种新的损失可以很容易地添加到任何现有的分类网络中,几乎没有计算开销。我们证明了我们的方法在 MNIST-USPS-SVHN、Office-31、Office-Home 和 Image CLEF-DA 基准上的有效性。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,导致在 Office-31 上与纯源模型相比绝对提升 9.4%,在 Image CLEF-DA 上提升 6.3%。这种新的损失可以很容易地添加到任何现有的分类网络中,几乎没有计算开销。我们证明了我们的方法在 MNIST-USPS-SVHN、Office-31、Office-Home 和 Image CLEF-DA 基准测试中的有效性。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判别性特征,导致在 Office-31 上与纯源模型相比绝对提升 9.4%,在 Image CLEF-DA 上提升 6.3%。这种新的损失可以很容易地添加到任何现有的分类网络中,几乎没有计算开销。我们证明了我们的方法在 MNIST-USPS-SVHN、Office-31、Office-Home 和 Image CLEF-DA 基准上的有效性。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,导致在 Office-31 上与纯源模型相比绝对提升 9.4%,在 Image CLEF-DA 上提升 6.3%。
更新日期:2021-01-01
down
wechat
bug