Robust unsupervised domain adaptation for neural networks via moment alignment
نویسندگان
چکیده
منابع مشابه
Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment
A novel approach for unsupervised domain adaptation for neural networks is proposed that relies on a metricbased regularization of the learning process. The metric-based regularization aims at domain-invariant latent feature representations by means of maximizing the similarity between domainspecific activation distributions. The proposed metric results from modifying an integral probability me...
متن کاملDeep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملSubspace Distribution Alignment for Unsupervised Domain Adaptation
We propose a novel method for unsupervised domain adaptation. Traditional machine learning algorithms often fail to generalize to new input distributions, causing reduced accuracy. Domain adaptation attempts to compensate for the performance degradation by transferring and adapting source knowledge to target domain. Existing unsupervised methods project domains into a lower-dimensional space an...
متن کاملCorrelation Alignment for Unsupervised Domain Adaptation
In this chapter, we present CORrelation ALignment (CORAL), a simple yet effective method for unsupervised domain adaptation. CORAL minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels. In contrast to subspace manifold methods, it aligns the original feature distributions of the source and target domains, rather th...
متن کاملJust DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation
The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and target domains. Alleviating the domain shift problem, especially in the challenging setting where no labeled data are available for the target domain, is par...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Information Sciences
سال: 2019
ISSN: 0020-0255
DOI: 10.1016/j.ins.2019.01.025