Domai adaptation 相关的句子

1. 

Domain adaptation addresses the problem of generalizing from asourcedistribution for which we have ample labeled training data to atargetdistribution for which we have little or no labels

Domain adaptation algorithms that do not use labeled target domain data are sometimes calledunsupervisedadaptation algorithms

Domain adaption tends to transfer knowledge across domains following dissimilar distribution and where target domain has inadequate labelled samples.

2.

Traditional machine learning algorithms work well under an assumption that training data in source domain and test data in target domain follow the same distribution. However, the real-world data may not follow this assumption due to the mismatch between training and test conditions. 

Classification methods traditionally work under the assumption that the training and test sets are sampled from similar distributions (domains). However, when such methods
are deployed in practise, the conditions in which test data is acquired do not exactly match those of the training set.

One of the problems of neural networks is that although they perform well on the samples generated from the same distribution as the training samples, they may find it difficult to correctly recognize samples from different distributions at the test time. One example is images collected from the Internet, which may come in abundance and be fully labeled. They have a distribution different from the images taken from a camera.

3.

Research on transfer learning has attracted more and more attention since 1995 in different names: learning to learn, life-long learning, knowledge transfer, inductive transfer, multitask learning, knowledge consolidation, context-sensitive learning, knowledge-based inductive bias, metalearning, and incremental/cumulative learning [20]

4. pseudo label

Most of the previous deep domain adaptation methods have been proposed mainly under the assumption that the adaptation can be realized by matching the distribution of features from different domains. These methods aimed to obtain domain-invariant features by minimizing the divergence between domains as well as a category loss on
the source domain (Ganin & Lempitsky, 2014; Long et al., 2015b; 2016). However, as shown in (Ben-David et al., 2010), theoretically, if a classifier that works well on both
the source and the target domains does not exist, we cannot expect a discriminative classifier for the target domain. That is, even if the distributions are matched on the nondiscriminative representations, the classifier may not work well on the target domain. Since directly learning discriminative representations for the target domain, in the absence of target labels, is considered very difficult, we propose to assign pseudo-labels to target samples and train targetspecific networks as if they were true labels

5.

Pan and Yang [22] presented taxonomy of TL methods which include Inductive TL, when labelled samples are available in both source and target domains; Transductive TL, when labels are only available in the source set, and Unsupervised TL, when labelled data is not present。