mlsanityData to 7 Oct 2026

AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation

arXiv 2107.10140 ↗First posted 21 Jul 2021cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints. We focus on source-free domain adaptation for semantic segmentation, wherein a source model must adapt itself to a new target domain given only unlabeled target data. We propose Augmentation Consistency-guided Self-training (AUGCO), a source-free adaptation algorithm that uses the model's pixel-level predictive consistency across diverse, automatically generated views of each target image along with model confidence to identify reliable pixel predictions, and selectively self-trains on those. AUGCO achieves state-of-the-art results for source-free adaptation on 3 standard benchmarks for semantic segmentation, all within a simple to implement and fast to converge method.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 56 of its 79 references that are in the map. First posted on arXiv 21 Jul 2021.

Builds on

56 of 79 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  8. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  10. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  11. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  12. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
38 more
  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  2. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  3. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  4. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  5. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  6. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  7. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  8. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  9. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  10. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  11. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  12. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 540
  13. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  14. 2019Confidence Regularized Self-Trainingcited by 418
  15. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  16. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 285
  17. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  18. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  19. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 235
  20. 2020Universal Source-Free Domain Adaptationcited by 219
  21. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  22. 2019Domain-Specific Batch Normalization for Unsupervised Domain Adaptationcited by 197
  23. 2018Progressive Feature Alignment for Unsupervised Domain Adaptationcited by 183
  24. 2020Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Datacited by 179
  25. 2020Instance Adaptive Self-Training for Unsupervised Domain Adaptationcited by 177
  26. 2017Image to Image Translation for Domain Adaptationcited by 171
  27. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  28. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  29. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  30. 2018Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mappingcited by 113
  31. 2020CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistencycited by 107
  32. 2019Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approachcited by 103
  33. 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
  34. 2020Domain Adaptation without Source Datacited by 88
  35. 2020SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptationcited by 78
  36. 2019Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentationcited by 74
  37. 2020Phase Consistent Ecological Domain Adaptationcited by 62
  38. 2020Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptationcited by 60

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 6; 2024: 4.

11 papers.

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  3. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  4. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  5. 2023Prompting Diffusion Representations for Cross-Domain Semantic Segmentationcited by 30
  6. 2024Reliable Source Approximation: Source-Free Unsupervised Domain Adaptation for Vestibular Schwannoma MRI Segmentationcited by 5
  7. 2024We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baselinecited by 4
  8. 2024PIG: Prompt Images Guidance for Night-Time Scene Parsingcited by 4
  9. 2023Single Image Test-Time Adaptation for Segmentationcited by 3
  10. 2024Cross-Domain Transfer Learning with CoRTe: Consistent and Reliable Transfer from Black-Box to Lightweight Segmentation Modelcited by 3
  11. 2023Generating Reliable Pixel-Level Labels for Source Free Domain Adaptationcited by 0