# DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation

arXiv: https://arxiv.org/abs/2107.09600 · HTML: https://mlsanity.com/paper/2107.09600/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 20 Jul 2021.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (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)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation](https://mlsanity.com/paper/1612.02649/) (2016)
- [DACS: Domain Adaptation via Cross-domain Mixed Sampling](https://mlsanity.com/paper/2007.08702/) (2020)
- [Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2003.03773/) (2020)
- [ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias](https://mlsanity.com/paper/2106.03348/) (2021)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision](https://mlsanity.com/paper/2004.07703/) (2020)
- [Instance Adaptive Self-Training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2008.12197/) (2020)
- [Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2003.00867/) (2020)
- [Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/1910.13049/) (2019)
- [Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1909.00589/) (2019)
- [Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things](https://mlsanity.com/paper/2011.08612/) (2020)
- [CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency](https://mlsanity.com/paper/2001.03182/) (2020)
- [Unsupervised Domain Adaptation in Semantic Segmentation: a Review](https://mlsanity.com/paper/2005.10876/) (2020)
- [Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2007.02424/) (2020)
- [Domain Adaptive Semantic Segmentation Using Weak Labels](https://mlsanity.com/paper/2007.15176/) (2020)
- [Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation](https://mlsanity.com/paper/2004.08878/) (2020)
- [MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2103.05254/) (2021)
- [Learning to Segment via Cut-and-Paste](https://mlsanity.com/paper/1803.06414/) (2018)
- [Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2007.14449/) (2020)

## Built on by (most cited first, 30 of 45)

- [MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation](https://mlsanity.com/paper/2212.01322/) (2022)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [An Empirical Study of Remote Sensing Pretraining](https://mlsanity.com/paper/2204.02825/) (2022)
- [CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation](https://mlsanity.com/paper/2207.09778/) (2022)
- [All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes](https://mlsanity.com/paper/2312.12176/) (2023)
- [BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation](https://mlsanity.com/paper/2204.02811/) (2022)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding](https://mlsanity.com/paper/2112.00484/) (2021)
- [Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation](https://mlsanity.com/paper/2308.14619/) (2023)
- [Domain-Agnostic Prior for Transfer Semantic Segmentation](https://mlsanity.com/paper/2204.02684/) (2022)
- [SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2203.15202/) (2022)
- [Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2403.10001/) (2024)
- [I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection](https://mlsanity.com/paper/2108.01343/) (2021)
- [Open-Set Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2405.19899/) (2024)
- [Deep Image Matting: A Comprehensive Survey](https://mlsanity.com/paper/2304.04672/) (2023)
- [Learning to Purification for Unsupervised Person Re-identification](https://mlsanity.com/paper/2204.09931/) (2022)
- [Augmentation-based Domain Generalization for Semantic Segmentation](https://mlsanity.com/paper/2304.12122/) (2023)
- [ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer](https://mlsanity.com/paper/2204.11891/) (2022)
- [Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2303.09779/) (2023)
- [Probabilistic Contrastive Learning for Domain Adaptation](https://mlsanity.com/paper/2111.06021/) (2021)
- [Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models](https://mlsanity.com/paper/2205.15781/) (2022)
- [Threshold-adaptive Unsupervised Focal Loss for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2208.10716/) (2022)
- [Unified Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2311.13254/) (2023)
- [Focus on Your Target: A Dual Teacher-Student Framework for Domain-adaptive Semantic Segmentation](https://mlsanity.com/paper/2303.09083/) (2023)
- [CoMaTrack: Competitive Multi-Agent Game-Theoretic Tracking with Vision-Language-Action Models](https://mlsanity.com/paper/2603.22846/) (2026)
- [Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2208.06100/) (2022)
- [Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2302.06992/) (2023)
- [Feedback-Driven Pseudo-Label Reliability Assessment: Redefining Thresholding for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2505.07691/) (2025)
- [Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation](https://mlsanity.com/paper/2312.06331/) (2023)
- [Gradient-based Class Weighting for Unsupervised Domain Adaptation in Dense Prediction Visual Tasks](https://mlsanity.com/paper/2407.01327/) (2024)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) for semantic segmentation aims to adapt a segmentation model trained on the labeled source domain to the unlabeled target domain. Existing methods try to learn domain invariant features while suffering from large domain gaps that make it difficult to correctly align discrepant features, especially in the initial training phase. To address this issue, we propose a novel Dual Soft-Paste (DSP) method in this paper. Specifically, DSP selects some classes from a source domain image using a long-tail class first sampling strategy and softly pastes the corresponding image patch on both the source and target training images with a fusion weight. Technically, we adopt the mean teacher framework for domain adaptation, where the pasted source and target images go through the student network while the original target image goes through the teacher network. Output-level alignment is carried out by aligning the probability maps of the target fused image from both networks using a weighted cross-entropy loss. In addition, feature-level alignment is carried out by aligning the feature maps of the source and target images from student network using a weighted maximum mean discrepancy loss. DSP facilitates the model learning domain-invariant features from the intermediate domains, leading to faster convergence and better performance. Experiments on two challenging benchmarks demonstrate the superiority of DSP over state-of-the-art methods. Code is available at urlhttps://github.com/GaoLii/DSP.