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

Source: [Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift](<https://www.sota2.com/research/paper/68fa66761e209131cea10409>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:50:28.993Z

Authors: Micha{\\l} Zaj\\k{a}c, Konrad Zolna, Stanis{\\l}aw Jastrz\\k{e}bski

Published: 2019-04-06T19:10:05.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1904.03515>)

[PDF](<https://arxiv.org/pdf/1904.03515.pdf>)