mlsanityData to 14 Oct 2026

Doubly Robust Self-Training

arXiv 2306.00265 ↗First posted 1 Jun 2023cs.LG cs.AI cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of self-training heavily relies on the accuracy of these pseudo-labels. In this paper, we introduce doubly robust self-training, a novel semi-supervised algorithm that provably balances between two extremes. When the pseudo-labels are entirely incorrect, our method reduces to a training process solely using labeled data. Conversely, when the pseudo-labels are completely accurate, our method transforms into a training process utilizing all pseudo-labeled data and labeled data, thus increasing the effective sample size. Through empirical evaluations on both the ImageNet dataset for image classification and the nuScenes autonomous driving dataset for 3D object detection, we demonstrate the superiority of the doubly robust loss over the standard self-training baseline.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 28 of its 55 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

28 of 55 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  7. 2020Knowledge Distillation: A Surveycited by 1,603
  8. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  9. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  10. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  11. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  12. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
16 more
  1. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  2. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
  3. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  4. 2023Prediction-Powered Inferencecited by 220
  5. 2022DaViT: Dual Attention Vision Transformerscited by 175
  6. 2019Orthogonal Statistical Learningcited by 151
  7. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 145
  8. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 116
  9. 20203DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detectioncited by 89
  10. 2022Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detectioncited by 48
  11. 2016Semi-supervised Inference: General Theory and Estimation of Meanscited by 38
  12. 2018De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representerscited by 34
  13. 2023Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detectioncited by 24
  14. 2022DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detectioncited by 20
  15. 2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19
  16. 2023DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detectioncited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 10; 2026: 3.

18 papers.

Sort:

By area:

  1. 2024Semi-Supervised Risk Control via Prediction-Powered Inferencecited by 13
  2. 2025Robust Reinforcement Learning from Human Feedback for Large Language Models Fine-Tuningcited by 13
  3. 2025How to Bridge the Sim-to-Real Gap in Digital Twin-Aided Telecommunication Networkscited by 6
  4. 2024Semi-Supervised U-statisticscited by 5
  5. 2025Prediction-Powered Semi-Supervised Learning with Online Power Tuningcited by 5
  6. 2024Automated Efficient Estimation using Monte Carlo Efficient Influence Functionscited by 4
  7. 2024Automatic AI Model Selection for Wireless Systems: Online Learning via Digital Twinningcited by 3
  8. 2025Do We Really Even Need Data? A Modern Look at Drawing Inference with Predicted Datacited by 3
  9. 2025Context-Aware Doubly-Robust Semi-Supervised Learningcited by 2
  10. 2025Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspectivecited by 2
  11. 2025Enhancing Semi-supervised Learning with Zero-shot Pseudolabelscited by 1
  12. 2025SADA: Safe and Adaptive Aggregation of Multiple Black-Box Predictions in Semi-Supervised Learningcited by 1
6 more
  1. 2025GeoTeacher: Geometry-Guided Semi-Supervised 3D Object Detectioncited by 1
  2. 2026DeDPO: Debiased Direct Preference Optimization for Diffusion Modelscited by 1
  3. 2024TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detectioncited by 0
  4. 2025Prediction-Augmented Trees for Reliable Statistical Inferencecited by 0
  5. 2026Learning U-Statistics with Active Inferencecited by 0
  6. 2026ABC-Align: Prediction-Powered Alignment with Adaptive Bias Controlcited by 0