2019/04/06 by Michał Zając, Zając, Michał, Konrad Zolna +5 · 4 citations
Computer Science · Mathematics · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1904.03515
Under review for ECML PKDD 2019
arxiv created 2019/04/06 · openalex publication_date 2019/04/06 · openalex created_date 2019/04/11 · arxiv updated 2019/10/07 · openalex updated_date 2026/07/28
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.