mlsanityData to 14 Oct 2026

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

arXiv 2207.09988 ↗First posted 20 Jul 2022cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations. It leverages a labeled source domain dataset as well as unlabeled target domain images to learn a segmentation network. In this paper, we observe two main issues of the existing domain-invariant learning framework. (1) Being distracted by the feature distribution alignment, the network cannot focus on the segmentation task. (2) Fitting source domain data well would compromise the target domain performance. To address these issues, we propose DecoupleNet that alleviates source domain overfitting and enables the final model to focus more on the segmentation task. Furthermore, we put forward Self-Discrimination (SD) and introduce an auxiliary classifier to learn more discriminative target domain features with pseudo labels. Finally, we propose Online Enhanced Self-Training (OEST) to contextually enhance the quality of pseudo labels in an online manner. Experiments show our method outperforms existing state-of-the-art methods, and extensive ablation studies verify the effectiveness of each component. Code is available at https://github.com/dvlab-research/DecoupleNet.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 77 of its 89 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

77 of 89 references.

References · 77

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2022Generative Adversarial Networkscited by 5,627
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  8. 2016Pyramid Scene Parsing Networkcited by 2,479
  9. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  10. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  11. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  12. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
38 more
  1. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  2. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  3. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  4. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
  5. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  6. 2016Least Squares Generative Adversarial Networkscited by 1,001
  7. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  8. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 718
  9. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  10. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  11. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  12. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  13. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  14. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 424
  15. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  16. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 341
  17. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  18. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  19. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  20. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  21. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  22. 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
  23. 2016Coupled Generative Adversarial Networkscited by 216
  24. 2019Domain-Specific Batch Normalization for Unsupervised Domain Adaptationcited by 197
  25. 2019Asymmetric Non-local Neural Networks for Semantic Segmentationcited by 196
  26. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  27. 2015ParseNet: Looking Wider to See Bettercited by 177
  28. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 177
  29. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  30. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  31. 2019Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentationcited by 151
  32. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  33. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  34. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
  35. 2019Domain-Symmetric Networks for Adversarial Domain Adaptationcited by 120
  36. 2021Semi-supervised Semantic Segmentation with Directional Context-aware Consistencycited by 112
  37. 2017No More Discrimination: Cross City Adaptation of Road Scene Segmenterscited by 111
  38. 2019Cluster Alignment with a Teacher for Unsupervised Domain Adaptationcited by 88

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 10; 2024: 7; 2025: 1; 2026: 2.

23 papers.

Sort:

By area:

  1. 2022MIC: Masked Image Consistency for Context-Enhanced Domain Adaptationcited by 178
  2. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 125
  3. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  4. 2024Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentationcited by 61
  5. 2022Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentationcited by 46
  6. 2024Unified Language-driven Zero-shot Domain Adaptationcited by 30
  7. 2023Diffusion-based Image Translation with Label Guidance for Domain Adaptive Semantic Segmentationcited by 27
  8. 2023Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentationcited by 26
  9. 2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancementcited by 19
  10. 2023To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentationcited by 14
  11. 2023Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentationcited by 11
  12. 2024Domain-adaptive Video Deblurring via Test-time Blurringcited by 8
11 more
  1. 2022Computational Imaging for Machine Perception: Transferring Semantic Segmentation beyond Aberrationscited by 7
  2. 2023Condition-Invariant Semantic Segmentationcited by 7
  3. 2024UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Frameworkcited by 6
  4. 2023A Chebyshev Confidence Guided Source-Free Domain Adaptation Framework for Medical Image Segmentationcited by 5
  5. 2024Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Datacited by 4
  6. 2025Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentationcited by 1
  7. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstractcited by 0
  8. 2024SimMAT: Exploring Transferability from Vision Foundation Models to Any Image Modalitycited by 0
  9. 2024Reducing Semantic Ambiguity In Domain Adaptive Semantic Segmentation Via Probabilistic Prototypical Pixel Contrastcited by 0
  10. 2026Using Unsupervised Domain Adaptation Semantic Segmentation for Pulmonary Embolism Detection in Computed Tomography Pulmonary Angiogram (CTPA) Imagescited by 0
  11. 2026Decouple, Purify and Unite: Semantic-Structural Prototype Learning for Federated Medical Segmentationcited by 0