mlsanityData to 7 Oct 2026

Domain Adaptive Video Segmentation via Temporal Consistency Regularization

arXiv 2107.11004 ↗First posted 23 Jul 2021cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Video semantic segmentation is an essential task for the analysis and understanding of videos. Recent efforts largely focus on supervised video segmentation by learning from fully annotated data, but the learnt models often experience clear performance drop while applied to videos of a different domain. This paper presents DA-VSN, a domain adaptive video segmentation network that addresses domain gaps in videos by temporal consistency regularization (TCR) for consecutive frames of target-domain videos. DA-VSN consists of two novel and complementary designs. The first is cross-domain TCR that guides the prediction of target frames to have similar temporal consistency as that of source frames (learnt from annotated source data) via adversarial learning. The second is intra-domain TCR that guides unconfident predictions of target frames to have similar temporal consistency as confident predictions of target frames. Extensive experiments demonstrate the superiority of our proposed domain adaptive video segmentation network which outperforms multiple baselines consistently by large margins.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 64 of its 82 references that are in the map. First posted on arXiv 23 Jul 2021.

Builds on

64 of 82 references.

References · 64

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  5. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  6. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  7. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  8. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
  9. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  10. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  11. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  12. 2019Confidence Regularized Self-Trainingcited by 418
38 more
  1. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  2. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
  3. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  4. 2020Space-Time Correspondence as a Contrastive Random Walkcited by 239
  5. 2020Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentationcited by 222
  6. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  7. 2016Deep Feature Flow for Video Recognitioncited by 186
  8. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  9. 2017Playing for Benchmarkscited by 169
  10. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
  11. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  12. 2019Domain Adaptation for Structured Output via Discriminative Patch Representationscited by 150
  13. 2020Video Panoptic Segmentationcited by 141
  14. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  15. 2018Improving Semantic Segmentation via Video Propagation and Label Relaxationcited by 134
  16. 2019Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentationcited by 126
  17. 2020Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentationcited by 126
  18. 2020Multi-Modal Domain Adaptation for Fine-Grained Action Recognitioncited by 115
  19. 2020MAST: A Memory-Augmented Self-supervised Trackercited by 109
  20. 2019Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approachcited by 103
  21. 2019Temporal Attentive Alignment for Large-Scale Video Domain Adaptationcited by 100
  22. 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
  23. 2018Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Videocited by 78
  24. 2020Temporally Distributed Networks for Fast Video Semantic Segmentationcited by 77
  25. 2016Semantic Video Segmentation by Gated Recurrent Flow Propagationcited by 76
  26. 2018Fully Convolutional Adaptation Networks for Semantic Segmentationcited by 75
  27. 2019Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentationcited by 74
  28. 2020Action Segmentation with Joint Self-Supervised Temporal Domain Adaptationcited by 74
  29. 2020Contextual-Relation Consistent Domain Adaptation for Semantic Segmentationcited by 70
  30. 2017Semantic Video CNNs through Representation Warpingcited by 65
  31. 2021Category Contrast for Unsupervised Domain Adaptation in Visual Taskscited by 65
  32. 2020Efficient Semantic Video Segmentation with Per-frame Inferencecited by 63
  33. 2018Low-Latency Video Semantic Segmentationcited by 61
  34. 2021Uncertainty-Aware Unsupervised Domain Adaptation in Object Detectioncited by 59
  35. 2016Clockwork Convnets for Video Semantic Segmentationcited by 55
  36. 2018Dynamic Video Segmentation Networkcited by 51
  37. 2019Adversarial Cross-Domain Action Recognition with Co-Attentioncited by 51
  38. 2021RDA: Robust Domain Adaptation via Fourier Adversarial Attackingcited by 48

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 7; 2024: 5; 2025: 2; 2026: 1.

21 papers.

Sort:

By area:

  1. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  2. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  3. 20233D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Cloudscited by 46
  4. 2024Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentationcited by 37
  5. 2022Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentationcited by 33
  6. 2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Miningcited by 30
  7. 2023GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentationcited by 22
  8. 2022Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Surveycited by 12
  9. 2022Domain Adaptive Video Segmentation via Temporal Pseudo Supervisioncited by 11
  10. 2023Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentationcited by 10
  11. 2023Temporal-aware Hierarchical Mask Classification for Video Semantic Segmentationcited by 7
  12. 2023Unified Domain Adaptive Semantic Segmentationcited by 6
9 more
  1. 2024Prompt-Driven Temporal Domain Adaptation for Nighttime UAV Trackingcited by 6
  2. 2024We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baselinecited by 4
  3. 2022Domain Adaptive Video Semantic Segmentation via Cross-Domain Moving Object Mixingcited by 3
  4. 2023MoDA: Leveraging Motion Priors from Videos for Advancing Unsupervised Domain Adaptation in Semantic Segmentationcited by 2
  5. 2025Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardizationcited by 2
  6. 2023Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptationcited by 1
  7. 2024PiPa++: Towards Unification of Domain Adaptive Semantic Segmentation via Self-supervised Learningcited by 1
  8. 2025Dual form Complementary Masking for Domain-Adaptive Image Segmentationcited by 1
  9. 2026See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learningcited by 0