24 citations · 46 across the 10 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 6 cited
Approximating Instance-Dependent Noise via Instance-Confidence Embedding
Yivan Zhang, Masashi Sugiyama
Label noise in multiclass classification is a major obstacle to the deployment of learning systems. However, unlike the widely used class-conditional noise (CCN) assumption that th…
stat.ML2021★ 24 cited
Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization
Yivan Zhang, Gang Niu, Masashi Sugiyama
Many weakly supervised classification methods employ a noise transition matrix to capture the class-conditional label corruption. To estimate the transition matrix from noisy data,…