Abstract | ||
---|---|---|
We raise the problem of regularizing Wasserstein means and propose several terms tailored to tackle different problems. Our formulation is based on variational transportation to distribute a sparse discrete measure into the target domain without mass splitting. The resulting sparse representation well captures the desired property of the domain while maintaining a small reconstruction error. We demonstrate the scalability and robustness of our method with examples of domain adaptation and skeleton layout. |
Year | Venue | DocType |
---|---|---|
2018 | arXiv: Learning | Journal |
Volume | Citations | PageRank |
abs/1812.00338 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mi Liang | 1 | 4 | 3.10 |
Wen Zhang | 2 | 6 | 8.84 |
Yalin Wang | 3 | 1042 | 79.53 |