HybridNet: Classification and Reconstruction Cooperation for Semi-supervised Learning

Abstract : In this paper, we introduce a new model for leveraging un-labeled 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 un-supervised 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 outper-form 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.
Complete list of metadatas

Cited literature [53 references]  Display  Hide  Download

https://hal.sorbonne-universite.fr/hal-02073640
Contributor : Thomas Robert <>
Submitted on : Wednesday, March 20, 2019 - 2:32:59 PM
Last modification on : Wednesday, October 9, 2019 - 4:11:17 PM
Long-term archiving on : Friday, June 21, 2019 - 8:27:30 PM

File

1807.11407.pdf
Files produced by the author(s)

Identifiers

Citation

Thomas Robert, Nicolas Thome, Matthieu Cord. HybridNet: Classification and Reconstruction Cooperation for Semi-supervised Learning. ECCV 2018 - 15th European Conference on Computer Vision, Sep 2018, Munich, Germany. pp.158-175, ⟨10.1007/978-3-030-01234-2_10⟩. ⟨hal-02073640⟩

Share

Metrics

Record views

180

Files downloads

32