Latent Class-Conditional Noise Model

Jiangchao Yao, Bo Han, Zhihan Zhou, Ya Zhang*, Ivor W. Tsang

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

5 Citations (Scopus)


Learning with noisy labels has become imperative in the Big Data era, which saves expensive human labors on accurate annotations. Previous noise-transition-based methods have achieved theoretically-grounded performance under the Class-Conditional Noise model (CCN). However, these approaches builds upon an ideal but impractical anchor set available to pre-estimate the noise transition. Even though subsequent works adapt the estimation as a neural layer, the ill-posed stochastic learning of its parameters in back-propagation easily falls into undesired local minimums. We solve this problem by introducing a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. By projecting the noise transition into the Dirichlet space, the learning is constrained on a simplex characterized by the complete dataset, instead of some ad-hoc parametric space wrapped by the neural layer. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels to train the classifier and to model the noise. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples. We further generalize LCCN to different counterparts compatible with open-set noisy labels, semi-supervised learning as well as cross-model training. A range of experiments demonstrate the advantages of LCCN and its variants over the current state-of-the-art methods. The code is available at here.

Original languageEnglish
Pages (from-to)9964-9980
Number of pages17
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number8
Early online date22 Feb 2023
Publication statusPublished - Aug 2023

Scopus Subject Areas

  • Software
  • Artificial Intelligence
  • Applied Mathematics
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics

User-Defined Keywords

  • Bayesian Modeling
  • Deep Learning
  • Noisy Supervision
  • Semi-Supervised Learning


Dive into the research topics of 'Latent Class-Conditional Noise Model'. Together they form a unique fingerprint.

Cite this