Partial Label Learning with Batch Label Correction

Authors

  • Yan Yan Northwestern Polytechnical University
  • Yuhong Guo Carleton University

DOI:

https://doi.org/10.1609/aaai.v34i04.6132

Abstract

Partial label (PL) learning tackles the problem where each training instance is associated with a set of candidate labels, among which only one is the true label. In this paper, we propose a simple but effective batch-based partial label learning algorithm named PL-BLC, which tackles the partial label learning problem with batch-wise label correction (BLC). PL-BLC dynamically corrects the label confidence matrix of each training batch based on the current prediction network, and adopts a MixUp data augmentation scheme to enhance the underlying true labels against the redundant noisy labels. In addition, it introduces a teacher model through a consistency cost to ensure the stability of the batch-based prediction network update. Extensive experiments are conducted on synthesized and real-world partial label learning datasets, while the proposed approach demonstrates the state-of-the-art performance for partial label learning.

Downloads

Published

2020-04-03

How to Cite

Yan, Y., & Guo, Y. (2020). Partial Label Learning with Batch Label Correction. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 6575-6582. https://doi.org/10.1609/aaai.v34i04.6132

Issue

Section

AAAI Technical Track: Machine Learning