English

Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift

Machine Learning 2019-10-07 v1 Machine Learning

Abstract

Recent work has shown that using unlabeled data in semi-supervised learning is not always beneficial and can even hurt generalization, especially when there is a class mismatch between the unlabeled and labeled examples. We investigate this phenomenon for image classification on the CIFAR-10 and the ImageNet datasets, and with many other forms of domain shifts applied (e.g. salt-and-pepper noise). Our main contribution is Split Batch Normalization (Split-BN), a technique to improve SSL when the additional unlabeled data comes from a shifted distribution. We achieve it by using separate batch normalization statistics for unlabeled examples. Due to its simplicity, we recommend it as a standard practice. Finally, we analyse how domain shift affects the SSL training process. In particular, we find that during training the statistics of hidden activations in late layers become markedly different between the unlabeled and the labeled examples.

Keywords

Cite

@article{arxiv.1904.03515,
  title  = {Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift},
  author = {Michał Zając and Konrad Zolna and Stanisław Jastrzębski},
  journal= {arXiv preprint arXiv:1904.03515},
  year   = {2019}
}

Comments

Under review for ECML PKDD 2019

R2 v1 2026-06-23T08:31:42.039Z