mlsanityData to 14 Oct 2026

Confidence Regularized Self-Training

arXiv 1908.09822 ↗First posted 26 Aug 2019cs.CV cs.LG cs.MMcited by 419

Not on the map. Why?

Abstract (arXiv)

Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident predictions as pseudo-labels for retraining. However, since pseudo-labels can be noisy, self-training can put overconfident label belief on wrong classes, leading to deviated solutions with propagated errors. To address the problem, we propose a confidence regularized self-training (CRST) framework, formulated as regularized self-training. Our method treats pseudo-labels as continuous latent variables jointly optimized via alternating optimization. We propose two types of confidence regularization: label regularization (LR) and model regularization (MR). CRST-LR generates soft pseudo-labels while CRST-MR encourages the smoothness on network output. Extensive experiments on image classification and semantic segmentation show that CRSTs outperform their non-regularized counterpart with state-of-the-art performance. The code and models of this work are available at https://github.com/yzou2/CRST.

Key facts. Cited by 419 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 126; 2022: 109; 2023: 98; 2024: 46; 2025: 28; 2026: 12.

419 papers.

Sort:

By area:

  1. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 300
  2. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  3. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 261
  4. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  5. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 164
  6. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 164
  7. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 159
  8. 2021Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Datacited by 152
  9. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  10. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 145
  11. 2021MIST: Multiple Instance Self-Training Framework for Video Anomaly Detectioncited by 138
  12. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
38 more
  1. 2021Cycle Self-Training for Domain Adaptationcited by 120
  2. 2021Learning to Track with Object Permanencecited by 119
  3. 2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 104
  4. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  5. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  6. 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 90
  7. 2022SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentationcited by 87
  8. 2022Self-Training: A Surveycited by 86
  9. 2021Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentationcited by 81
  10. 2021Bootstrapping Semantic Segmentation with Regional Contrastcited by 80
  11. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  12. 2021PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Trainingcited by 80
  13. 2021Context-Aware Mixup for Domain Adaptive Semantic Segmentationcited by 79
  14. 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
  15. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  16. 2022MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentationcited by 76
  17. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  18. 2022Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentationcited by 72
  19. 2021Category Contrast for Unsupervised Domain Adaptation in Visual Taskscited by 65
  20. 2023Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correctioncited by 65
  21. 2022Safe Self-Refinement for Transformer-based Domain Adaptationcited by 61
  22. 2022PODA: Prompt-driven Zero-shot Domain Adaptationcited by 60
  23. 2021ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 57
  24. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 57
  25. 2022CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentationcited by 54
  26. 2021Test-time Batch Statistics Calibration for Covariate Shiftcited by 50
  27. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 50
  28. 2021RDA: Robust Domain Adaptation via Fourier Adversarial Attackingcited by 48
  29. 2021Learning Cross-modal Contrastive Features for Video Domain Adaptationcited by 47
  30. 2022Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentationcited by 47
  31. 2022Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detectioncited by 47
  32. 2023Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentationcited by 47
  33. 2021Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentationcited by 46
  34. 2022Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentationcited by 46
  35. 20233D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Cloudscited by 46
  36. 2021Improved Regularization and Robustness for Fine-tuning in Neural Networkscited by 45
  37. 2021Federated Multi-Target Domain Adaptationcited by 44
  38. 2021Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Densitycited by 44

50 most cited of 419 All 419 (JSON)