Log In Sign Up

A Unified Joint Maximum Mean Discrepancy for Domain Adaptation

by   Wei Wang, et al.

Domain adaptation has received a lot of attention in recent years, and many algorithms have been proposed with impressive progress. However, it is still not fully explored concerning the joint probability distribution (P(X, Y)) distance for this problem, since its empirical estimation derived from the maximum mean discrepancy (joint maximum mean discrepancy, JMMD) will involve complex tensor-product operator that is hard to manipulate. To solve this issue, this paper theoretically derives a unified form of JMMD that is easy to optimize, and proves that the marginal, class conditional and weighted class conditional probability distribution distances are our special cases with different label kernels, among which the weighted class conditional one not only can realize feature alignment across domains in the category level, but also deal with imbalance dataset using the class prior probabilities. From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one. Therefore, we leverage Hilbert Schmidt independence criterion and propose a novel MMD matrix to promote the dependence, and devise a novel label kernel that is robust to label distribution shift. Finally, we conduct extensive experiments on several cross-domain datasets to demonstrate the validity and effectiveness of the revealed theoretical results.


Conditional Bures Metric for Domain Adaptation

As a vital problem in classification-oriented transfer, unsupervised dom...

Correlated Adversarial Joint Discrepancy Adaptation Network

Domain adaptation aims to mitigate the domain shift problem when transfe...

Transferability versus Discriminability: Joint Probability Distribution Adaptation (JPDA)

Transfer learning makes use of data or knowledge in one task to help sol...

Rethink Maximum Mean Discrepancy for Domain Adaptation

Existing domain adaptation methods aim to reduce the distributional diff...

Bures Joint Distribution Alignment with Dynamic Margin for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) is one of the prominent tasks of tr...

Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation

Existing works typically treat cross-domain semantic segmentation (CDSS)...

Learning Kernel for Conditional Moment-Matching Discrepancy-based Image Classification

Conditional Maximum Mean Discrepancy (CMMD) can capture the discrepancy ...