# Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/2203.02792 · HTML: https://mlsanity.com/paper/2203.02792/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 67 references that are in the map.
- First posted on arXiv 5 Mar 2022.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [High-Resolution Representations for Labeling Pixels and Regions](https://mlsanity.com/paper/1904.04514/) (2019)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation](https://mlsanity.com/paper/1502.02734/) (2015)
- [ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2106.05095/) (2021)
- [Adversarial Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1802.07934/) (2018)
- [FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference](https://mlsanity.com/paper/1902.10421/) (2019)
- [Semi-Supervised Semantic Segmentation with High- and Low-level Consistency](https://mlsanity.com/paper/1908.05724/) (2019)
- [OCNet: Object Context Network for Scene Parsing](https://mlsanity.com/paper/1809.00916/) (2018)
- [Data augmentation using learned transformations for one-shot medical image segmentation](https://mlsanity.com/paper/1902.09383/) (2019)
- [Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank](https://mlsanity.com/paper/2104.13415/) (2021)

## Built on by (most cited first, 9 of 9)

- [A Survey on Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2302.09899/) (2023)
- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [Weakly Supervised Semantic Segmentation by Knowledge Graph Inference](https://mlsanity.com/paper/2309.14057/) (2023)
- [Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2505.23438/) (2025)
- [L-MAE: Masked Autoencoders are Semantic Segmentation Datasets Augmenter](https://mlsanity.com/paper/2211.11242/) (2022)
- [Exploiting Minority Pseudo-Labels for Semi-Supervised Fine-grained Road Scene Understanding](https://mlsanity.com/paper/2409.12680/) (2024)
- [SP 3 : Superpixel-propagated pseudo-label learning for weakly semi-supervised medical image segmentation](https://mlsanity.com/paper/2411.11636/) (2024)
- [Bidirectional Uncertainty-Aware Region Learning for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2502.07457/) (2025)
- [TC-ADA: One-Shot Active Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2609.33432/) (2026)

## Abstract (arXiv)

A common challenge posed to robust semantic segmentation is the expensive data annotation cost. Existing semi-supervised solutions show great potential for solving this problem. Their key idea is constructing consistency regularization with unsupervised data augmentation from unlabeled data for model training. The perturbations for unlabeled data enable the consistency training loss, which benefits semi-supervised semantic segmentation. However, these perturbations destroy image context and introduce unnatural boundaries, which is harmful for semantic segmentation. Besides, the widely adopted semi-supervised learning framework, i.e. mean-teacher, suffers performance limitation since the student model finally converges to the teacher model. In this paper, first of all, we propose a context friendly differentiable geometric warping to conduct unsupervised data augmentation; secondly, a novel adversarial dual-student framework is proposed to improve the Mean-Teacher from the following two aspects: (1) dual student models are learned independently except for a stabilization constraint to encourage exploiting model diversities; (2) adversarial training scheme is applied to both students and the discriminators are resorted to distinguish reliable pseudo-label of unlabeled data for self-training. Effectiveness is validated via extensive experiments on PASCAL VOC2012 and Cityscapes. Our solution significantly improves the performance and state-of-the-art results are achieved on both datasets. Remarkably, compared with fully supervision, our solution achieves comparable mIoU of 73.4% using only 12.5% annotated data on PASCAL VOC2012. Our codes and models are available at https://github.com/cao-cong/ADS-SemiSeg.