Interpolation Consistency Training for Semi-Supervised Learning

@article{Verma2019InterpolationCT,
  title={Interpolation Consistency Training for Semi-Supervised Learning},
  author={Vikas Verma and Alex Lamb and Juho Kannala and Yoshua Bengio and David Lopez-Paz},
  journal={ArXiv},
  year={2019},
  volume={abs/1903.03825}
}
We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. [...] Key Result 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.Expand
Unsupervised Data Augmentation for Consistency Training
Semi-Supervised Audio Classification with Consistency-Based Regularization
Density-Aware Graph for Deep Semi-Supervised Visual Recognition
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning
Mask-based Data Augmentation for Semi-supervised Semantic Segmentation
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 35 REFERENCES
Temporal Ensembling for Semi-Supervised Learning
Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
Smooth Neighbors on Teacher Graphs for Semi-Supervised Learning
Manifold regularization with GANs for semi-supervised learning
Manifold Mixup: Better Representations by Interpolating Hidden States
Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
Semi-Supervised Learning
...
1
2
3
4
...