当前位置: X-MOL 学术Neural Process Lett. › 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.)
Unsupervised Domain Adaptation via Discriminative Classes-Center Feature Learning in Adversarial Network
Neural Processing Letters ( IF 2.6 ) Pub Date : 2020-05-21 , DOI: 10.1007/s11063-020-10266-z
Wendong Chen , Haifeng Hu

Adversarial learning has achieved remarkable advance in learning transferable representations across different domains. Generally, previous works are mainly devoted to reducing domain shift between labeled source data and unlabeled target data by extracting domain-invariant features. However, these adversarial methods rarely consider task-specific decision boundaries among classes, causing classification performance degradation in cross domain tasks. In this paper, we propose a novel approach for the task of unsupervised domain adaptation via discriminative classes-center feature learning in adversarial network (C2FAN), which concentrates on learning domain-invariant representation and paying close attention to classification decision boundary simultaneously to improve the ability of transferable knowledge across different domains. C2FAN consists of a feature extractor, a classifier and a discriminator. Firstly, for reducing domain gaps between source and target domains in the feature extractor, we propose to utilize a conditional adversarial learning module to extract domain-invariant feature and improve discriminability of the classifier simultaneously. Further, we present a high-efficiency layer normalization module to reduce domain shift existing in the classifier. Secondly, we design a discriminative classes-center feature learning module in the classifier to diminish the distribution distance of the same-class samples so that the decision boundary can distinguish different classes easily, which can reduce the misclassification on target samples. What’s more, C2FAN is an effective yet considerable simple approach which can be embedded into current domain adaptation approaches conveniently. Extensive experiments demonstrate that our proposed model achieves satisfactory results on some standard domain adaptation benchmarks.

中文翻译:

对抗性分类中基于分类类的无监督域自适应-对抗网络中的特征学习

对抗学习在学习跨不同领域的可转移表示形式方面已取得了显着进步。通常,先前的工作主要致力于通过提取域不变特征来减少标记源数据和未标记目标数据之间的域偏移。但是,这些对抗方法很少考虑类之间特定于任务的决策边界,从而导致跨域任务中的分类性能下降。在本文中,我们提出了一种新颖的方法,用于通过对抗性网络(C 2 FAN)中的判别类-中心特征学习来实现无监督域自适应的任务。),它专注于学习领域不变表示,并同时密切关注分类决策边界,以提高跨领域的知识转移能力。C 2风扇由特征提取器,分类器和鉴别器组成。首先,为了减少特征提取器中源域和目标域之间的域间隙,我们提出利用条件对抗学习模块提取域不变特征并同时提高分类器的可分辨性。此外,我们提出了一个高效的层归一化模块,以减少分类器中存在的域移位。其次,我们在分类器中设计了一个判别类中心特征学习模块,以减少同一类样本的分布距离,使决策边界可以轻松地区分不同类别,从而减少目标样本的误分类。此外,C 2风扇是一种有效但相当简单的方法,可以方便地嵌入到当前的域适应方法中。大量实验表明,我们提出的模型在某些标准域自适应基准上取得了令人满意的结果。
更新日期:2020-05-21
down
wechat
bug