English

HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning

Machine Learning 2018-07-31 v1 Machine Learning

Abstract

In this paper, we introduce a new model for leveraging unlabeled data to improve generalization performances of image classifiers: a two-branch encoder-decoder architecture called HybridNet. The first branch receives supervision signal and is dedicated to the extraction of invariant class-related representations. The second branch is fully unsupervised and dedicated to model information discarded by the first branch to reconstruct input data. To further support the expected behavior of our model, we propose an original training objective. It favors stability in the discriminative branch and complementarity between the learned representations in the two branches. HybridNet is able to outperform state-of-the-art results on CIFAR-10, SVHN and STL-10 in various semi-supervised settings. In addition, visualizations and ablation studies validate our contributions and the behavior of the model on both CIFAR-10 and STL-10 datasets.

Keywords

Cite

@article{arxiv.1807.11407,
  title  = {HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning},
  author = {Thomas Robert and Nicolas Thome and Matthieu Cord},
  journal= {arXiv preprint arXiv:1807.11407},
  year   = {2018}
}

Comments

Accepted at ECCV 2018

R2 v1 2026-06-23T03:19:11.842Z