mlsanityData to 7 Oct 2026

Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation

arXiv 2104.02633 ↗First posted 6 Apr 2021cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Deep convolutional neural networks for semantic segmentation achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the training data; second, they require a huge amount of labeled data for their optimization. In this paper, we introduce feature-level space-shaping regularization strategies to reduce the domain discrepancy in semantic segmentation. In particular, for this purpose we jointly enforce a clustering objective, a perpendicularity constraint and a norm alignment goal on the feature vectors corresponding to source and target samples. Additionally, we propose a novel measure able to capture the relative efficacy of an adaptation strategy compared to supervised training. We verify the effectiveness of such methods in the autonomous driving setting achieving state-of-the-art results in multiple synthetic-to-real road scenes benchmarks.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 40 of its 55 references that are in the map. First posted on arXiv 6 Apr 2021.

Builds on

40 of 55 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  9. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  10. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  11. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  12. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
28 more
  1. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  2. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 546
  3. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  4. 2019Confidence Regularized Self-Trainingcited by 418
  5. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  6. 2015Return of Frustratingly Easy Domain Adaptationcited by 389
  7. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  8. 2020DACS: Domain Adaptation via Cross-domain Mixed Samplingcited by 226
  9. 2017Image to Image Translation for Domain Adaptationcited by 171
  10. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  11. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  12. 2020CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistencycited by 107
  13. 2017Adversarial Dropout Regularizationcited by 106
  14. 2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
  15. 2020Unsupervised Domain Adaptation in Semantic Segmentation: a Reviewcited by 88
  16. 2017Unsupervised Domain Adaptation with Similarity Learningcited by 73
  17. 2019Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptationcited by 62
  18. 2020Spatial Attention Pyramid Network for Unsupervised Domain Adaptationcited by 56
  19. 2019Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labelingcited by 53
  20. 2017Adversarial Dropout for Supervised and Semi-supervised Learningcited by 38
  21. 2014Fully Convolutional Multi-Class Multiple Instance Learningcited by 37
  22. 2019Domain Bridge for Unpaired Image-to-Image Translation and Unsupervised Domain Adaptationcited by 32
  23. 2020Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignmentcited by 29
  24. 2020Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddingscited by 25
  25. 2019Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentationcited by 22
  26. 2020Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Trainingcited by 10
  27. 2020Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learningcited by 7
  28. 2020Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classificationcited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 3; 2024: 2; 2025: 1.

10 papers.

  1. 2024Can We Leave Deepfake Data Behind in Training Deepfake Detector?cited by 48
  2. 2022Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learningcited by 35
  3. 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
  4. 2022SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpointscited by 22
  5. 2023Advancing Bayesian Optimization via Learning Correlated Latent Spacecited by 18
  6. 2023Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learningcited by 9
  7. 2022Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentationcited by 6
  8. 2021Road Scenes Segmentation Across Different Domains by Disentangling Latent Representationscited by 5
  9. 2024A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimationcited by 2
  10. 2025TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justificationcited by 2