# Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/1506.04924 · HTML: https://mlsanity.com/paper/1506.04924/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2015.

## Built on by (most cited first, 23 of 23)

- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals](https://mlsanity.com/paper/2102.06191/) (2021)
- [Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2206.06363/) (2022)
- [CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2306.04300/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Semi-supervised Multi-task Learning for Semantics and Depth](https://mlsanity.com/paper/2110.07197/) (2021)
- [Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation](https://mlsanity.com/paper/2105.14732/) (2021)
- [Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review](https://mlsanity.com/paper/2203.10939/) (2022)
- [Semi-Supervised Semantic Segmentation of Vessel Images using Leaking Perturbations](https://mlsanity.com/paper/2110.11998/) (2021)
- [Seg4Reg+: Consistency Learning between Spine Segmentation and Cobb Angle Regression](https://mlsanity.com/paper/2208.12462/) (2022)
- [LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training](https://mlsanity.com/paper/2308.11239/) (2023)
- [Weak-shot Semantic Segmentation by Transferring Semantic Affinity and Boundary](https://mlsanity.com/paper/2110.01519/) (2021)
- [Segmentation with mixed supervision: Confidence maximization helps knowledge distillation](https://mlsanity.com/paper/2109.10902/) (2021)
- [ALPS: An Auto-Labeling and Pre-training Scheme for Remote Sensing Segmentation With Segment Anything Model](https://mlsanity.com/paper/2406.10855/) (2024)
- [FODVid: Flow-guided Object Discovery in Videos](https://mlsanity.com/paper/2307.04392/) (2023)
- [HDC: Hierarchical Distillation for Multi-level Noisy Consistency in Semi-Supervised Fetal Ultrasound Segmentation](https://mlsanity.com/paper/2504.09876/) (2025)
- [Exploiting Elasticity in Tensor Ranks for Compressing Neural Networks](https://mlsanity.com/paper/2105.04218/) (2021)
- [Bi-directional Loop Closure for Visual SLAM](https://mlsanity.com/paper/2204.01524/) (2022)
- [TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency](https://mlsanity.com/paper/2210.05152/) (2022)
- [WeatherProof: Leveraging Language Guidance for Semantic Segmentation in Adverse Weather](https://mlsanity.com/paper/2403.14874/) (2024)
- [Open-Ended CT Volume Segmentation with Weak Supervision from Language](https://mlsanity.com/paper/2607.25860/) (2026)
- [TricycleGAN: Unsupervised Image Synthesis and Segmentation Based on Shape Priors](https://mlsanity.com/paper/2102.02690/) (2021)
- [TPPI-Net: Towards Efficient and Practical Hyperspectral Image Classification](https://mlsanity.com/paper/2103.10084/) (2021)

## Abstract (arXiv)

We propose a novel deep neural network architecture for semi-supervised semantic segmentation using heterogeneous annotations. Contrary to existing approaches posing semantic segmentation as a single task of region-based classification, our algorithm decouples classification and segmentation, and learns a separate network for each task. In this architecture, labels associated with an image are identified by classification network, and binary segmentation is subsequently performed for each identified label in segmentation network. The decoupled architecture enables us to learn classification and segmentation networks separately based on the training data with image-level and pixel-wise class labels, respectively. It facilitates to reduce search space for segmentation effectively by exploiting class-specific activation maps obtained from bridging layers. Our algorithm shows outstanding performance compared to other semi-supervised approaches even with much less training images with strong annotations in PASCAL VOC dataset.