资源分类
》 资源 》论文》Interpolation Consistency Training for Semi-Supervised Learning

Interpolation Consistency Training for Semi-Supervised Learning

2019-10-08 | |  170 |   69 |   0

Abstract We introduce Interpolation Consistency Training (ICT), a simple and computation effificient algorithm for training Deep Neural Networks in the semisupervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classifification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark datasets.

上一篇：Object Detection based Deep Unsupervised Hashing

下一篇：Quadruply Stochastic Gradients for Large Scale Nonlinear Semi-Supervised AUC Optimization

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...