SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning

SoLar: a novel Optimal Transport-based framework for partial-label learning, allowing to refine the disambiguated labels towards matching the marginal class prior distribution.

Data and Resources

Cite this as

Haobo Wang, Mingxuan Xia, Yixuan Li, Yuren Mao, Lei Feng, Gang Chen, Junbo Zhao (2025). Dataset: SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning. https://doi.org/10.57702/e25o2cnb

DOI retrieved: January 3, 2025

Additional Info

Field Value
Created January 3, 2025
Last update January 3, 2025
Defined In https://doi.org/10.48550/arXiv.2209.10365
Author Haobo Wang
More Authors
Mingxuan Xia
Yixuan Li
Yuren Mao
Lei Feng
Gang Chen
Junbo Zhao
Homepage https://github.com/hbzju/SoLar