English

Semi-Supervised Learning via New Deep Network Inversion

Machine Learning 2017-11-15 v1 Machine Learning

Abstract

We exploit a recently derived inversion scheme for arbitrary deep neural networks to develop a new semi-supervised learning framework that applies to a wide range of systems and problems. The approach outperforms current state-of-the-art methods on MNIST reaching 99.14%99.14\% of test set accuracy while using 55 labeled examples per class. Experiments with one-dimensional signals highlight the generality of the method. Importantly, our approach is simple, efficient, and requires no change in the deep network architecture.

Keywords

Cite

@article{arxiv.1711.04313,
  title  = {Semi-Supervised Learning via New Deep Network Inversion},
  author = {Randall Balestriero and Vincent Roger and Herve G. Glotin and Richard G. Baraniuk},
  journal= {arXiv preprint arXiv:1711.04313},
  year   = {2017}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1710.09302

R2 v1 2026-06-22T22:43:27.773Z