Machine Learning

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

Tagged: , , ,

This topic contains 0 replies, has 1 voice, and was last updated by  arXiv 12 months ago.


  • arXiv
    5 pts

    Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

    The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, and penalizes predictions that are inconsistent with this target. However, because the targets change only once per epoch, Temporal Ensembling becomes unwieldy when learning large datasets. To overcome this problem, we propose Mean Teacher, a method that averages model weights instead of label predictions. As an additional benefit, Mean Teacher improves test accuracy and enables training with fewer labels than Temporal Ensembling. Without changing the network architecture, Mean Teacher achieves an error rate of 4.35% on SVHN with 250 labels, outperforming Temporal Ensembling trained with 1000 labels. We also show that a good network architecture is crucial to performance. Combining Mean Teacher and Residual Networks, we improve the state of the art on CIFAR-10 with 4000 labels from 10.55% to 6.28%, and on ImageNet 2012 with 10% of the labels from 35.24% to 9.11%.

    Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
    by Antti Tarvainen, Harri Valpola
    https://arxiv.org/pdf/1703.01780v4.pdf

You must be logged in to reply to this topic.