Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift
arXiv:1904.03515
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.
arXiv commentUnder review for ECML PKDD 2019
References in corpus (10)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Temporal Ensembling for Semi-Supervised Learning
- ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
- Revisiting Batch Normalization For Practical Domain Adaptation
- A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
- A Closer Look at Memorization in Deep Networks
- Measuring the tendency of CNNs to Learn Surface Statistical Regularities
- Learning Robust Representations by Projecting Superficial Statistics Out
- Mode Normalization