# Structured Consistency Loss for semi-supervised semantic segmentation

arXiv: https://arxiv.org/abs/2001.04647 · HTML: https://mlsanity.com/paper/2001.04647/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2020.

## Built on by (most cited first, 30 of 40)

- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.09025/) (2021)
- [Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning](https://mlsanity.com/paper/2110.05474/) (2021)
- [Scribble-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2203.08537/) (2022)
- [Adaptive Early-Learning Correction for Segmentation from Noisy Annotations](https://mlsanity.com/paper/2110.03740/) (2021)
- [Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentation](https://mlsanity.com/paper/2201.08657/) (2022)
- [ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes](https://mlsanity.com/paper/2106.02740/) (2021)
- [Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2308.12595/) (2023)
- [ConfMix: Unsupervised Domain Adaptation for Object Detection via Confidence-based Mixing](https://mlsanity.com/paper/2210.11539/) (2022)
- [Diverse Cotraining Makes Strong Semi-Supervised Segmentor](https://mlsanity.com/paper/2308.09281/) (2023)
- [MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection](https://mlsanity.com/paper/2111.10958/) (2021)
- [Decoder Denoising Pretraining for Semantic Segmentation](https://mlsanity.com/paper/2205.11423/) (2022)
- [Semi-Mamba-UNet: Pixel-Level Contrastive and Pixel-Level Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2402.07245/) (2024)
- [Fuzzy Positive Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2210.08519/) (2022)
- [A Survey on Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2302.09899/) (2023)
- [Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2211.16701/) (2022)
- [Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images](https://mlsanity.com/paper/2110.07782/) (2021)
- [Semi-supervised Semantic Segmentation with Multi-Constraint Consistency Learning](https://mlsanity.com/paper/2503.17914/) (2025)
- [Mask-based Data Augmentation for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2101.10156/) (2021)
- [SegMatch: A semi-supervised learning method for surgical instrument segmentation](https://mlsanity.com/paper/2308.05232/) (2023)
- [Semi-supervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2110.10639/) (2021)
- [Semi-Supervised Semantic Segmentation With Region Relevance](https://mlsanity.com/paper/2304.11539/) (2023)
- [Diffusion-Refined VQA Annotations for Semi-Supervised Gaze Following](https://mlsanity.com/paper/2406.02774/) (2024)
- [Pose-MUM : Reinforcing Key Points Relationship for Semi-Supervised Human Pose Estimation](https://mlsanity.com/paper/2203.07837/) (2022)
- [STEdge: Self-training Edge Detection with Multi-layer Teaching and Regularization](https://mlsanity.com/paper/2201.05121/) (2022)
- [Consistency Regularization for Domain Adaptation](https://mlsanity.com/paper/2208.11084/) (2022)
- [Semi-weakly-supervised neural network training for medical image registration](https://mlsanity.com/paper/2402.10728/) (2024)
- [Multi-Class 3D Object Detection with Single-Class Supervision](https://mlsanity.com/paper/2205.05703/) (2022)
- [Online pseudo labeling for polyp segmentation with momentum networks](https://mlsanity.com/paper/2209.14599/) (2022)
- [The Effects of Mixed Sample Data Augmentation are Class Dependent](https://mlsanity.com/paper/2307.09136/) (2023)

## Abstract (arXiv)

The consistency loss has played a key role in solving problems in recent studies on semi-supervised learning. Yet extant studies with the consistency loss are limited to its application to classification tasks; extant studies on semi-supervised semantic segmentation rely on pixel-wise classification, which does not reflect the structured nature of characteristics in prediction. We propose a structured consistency loss to address this limitation of extant studies. Structured consistency loss promotes consistency in inter-pixel similarity between teacher and student networks. Specifically, collaboration with CutMix optimizes the efficient performance of semi-supervised semantic segmentation with structured consistency loss by reducing computational burden dramatically. The superiority of proposed method is verified with the Cityscapes; The Cityscapes benchmark results with validation and with test data are 81.9 mIoU and 83.84 mIoU respectively. This ranks the first place on the pixel-level semantic labeling task of Cityscapes benchmark suite. To the best of our knowledge, we are the first to present the superiority of state-of-the-art semi-supervised learning in semantic segmentation.