# HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning

arXiv: https://arxiv.org/abs/1807.11407 · HTML: https://mlsanity.com/paper/1807.11407/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2018.

## Built on by (most cited first, 8 of 8)

- [Discrepancy-Guided Reconstruction Learning for Image Forgery Detection](https://mlsanity.com/paper/2304.13349/) (2023)
- [Specularity Factorization for Low-Light Enhancement](https://mlsanity.com/paper/2404.01998/) (2024)
- [Hybrid Supervision Learning for Pathology Whole Slide Image Classification](https://mlsanity.com/paper/2107.00934/) (2021)
- [PatchMix Augmentation to Identify Causal Features in Few-shot Learning](https://mlsanity.com/paper/2211.16019/) (2022)
- [unORANIC: Unsupervised Orthogonalization of Anatomy and Image-Characteristic Features](https://mlsanity.com/paper/2308.15507/) (2023)
- [R2-D2: Repetitive Reprediction Deep Decipher for Semi-Supervised Deep Learning](https://mlsanity.com/paper/2202.08955/) (2022)
- [Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classification](https://mlsanity.com/paper/2203.07027/) (2022)
- [Transfer Learning with Reconstruction Loss](https://mlsanity.com/paper/2404.00505/) (2024)

## Abstract (arXiv)

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.