Nov 13, 2019 · In this work, we propose two improved MMD metrics, ie, weighted MMD (WMMD) and class-specific MMD (CMMD), to alleviate the adverse effect caused by the changes ...

In domain adaptation, maximum mean discrepancy (M-. MD) has ... that weighted DAN can outperform DAN on a variety of unsupervised domain adaptation tasks.

May 1, 2017 · We show that MMD cannot account for class weight bias and results in degraded domain adaptation performance. To address this issue, a weighted ...

Abstract—Although maximum mean discrepancy (MMD) has achieved great success in unsupervised domain adaptation (UDA), most of existing UDA methods ignore the ...

Experiments show that, both WMMD and CMMD benefit the classification accuracy, and the CWDAN can achieve compelling UDA performance in comparison with MMD ...

In this work, we propose two improved MMD metrics, i.e., weighted MMD (WMMD) and class-specific MMD (CMMD), to alleviate the adverse effect caused by the ...

It is shown that MMD cannot account for class weight bias and results in degraded domain adaptation performance and a weighted MMD model is proposed, ...

Missing: Specific | Show results with:Specific

Yan et al. [33] explored the use of weighted MMD to mitigate class weight bias and improve domain adaptation outcomes. Addressing the challenge of noisy labels ...

This is an implementation of CVPR17 paper "Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation".