Timezone: »

 
Poster
Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning
Yu Yao · Tongliang Liu · Bo Han · Mingming Gong · Jiankang Deng · Gang Niu · Masashi Sugiyama

Thu Dec 10 09:00 PM -- 11:00 PM (PST) @ Poster Session 6 #1821
The transition matrix, denoting the transition relationship from clean labels to noisy labels, is essential to build statistically consistent classifiers in label-noise learning. Existing methods for estimating the transition matrix rely heavily on estimating the noisy class posterior. However, the estimation error for noisy class posterior could be large because of the randomness of label noise. The estimation error would lead the transition matrix to be poorly estimated. Therefore in this paper, we aim to solve this problem by exploiting the divide-and-conquer paradigm. Specifically, we introduce an intermediate class to avoid directly estimating the noisy class posterior. By this intermediate class, the original transition matrix can then be factorized into the product of two easy-to-estimated transition matrices. We term the proposed method as the dual $T$-estimator. Both theoretical analyses and empirical results illustrate the effectiveness of the dual $T$-estimator for estimating transition matrices, leading to better classification performances.

Author Information

Nick Yao (University of Sydney)
Tongliang Liu (The University of Sydney)
Bo Han (HKBU / RIKEN)
Mingming Gong (University of Melbourne)
Jiankang Deng (Imperial College London)
Gang Niu (RIKEN)
Masashi Sugiyama (RIKEN / University of Tokyo)

More from the Same Authors