mlsanityData to 7 Oct 2026

Learning with Pseudo-Ensembles

arXiv 1412.4864 ↗First posted 16 Dec 2014stat.ML cs.LG cs.NEcited by 241

Not on the map. Why?

Abstract (arXiv)

We formalize the notion of a pseudo-ensemble, a (possibly infinite) collection of child models spawned from a parent model by perturbing it according to some noise process. E.g., dropout (Hinton et. al, 2012) in a deep neural network trains a pseudo-ensemble of child subnetworks generated by randomly masking nodes in the parent network. We present a novel regularizer based on making the behavior of a pseudo-ensemble robust with respect to the noise process generating it. In the fully-supervised setting, our regularizer matches the performance of dropout. But, unlike dropout, our regularizer naturally extends to the semi-supervised setting, where it produces state-of-the-art results. We provide a case study in which we transform the Recursive Neural Tensor Network of (Socher et. al, 2013) into a pseudo-ensemble, which significantly improves its performance on a real-world sentiment analysis benchmark.

Key facts. Cited by 241 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 54; 2022: 61; 2023: 58; 2024: 45; 2025: 18; 2026: 5.

241 papers.

Sort:

By area:

  1. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  2. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  3. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  4. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  5. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  6. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  7. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 147
  8. 2021Cycle Self-Training for Domain Adaptationcited by 120
  9. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 112
  10. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  11. 2022Prompt Consistency for Zero-Shot Task Generalizationcited by 66
  12. 2022BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotationcited by 54
38 more
  1. 2024AutoEval Done Right: Using Synthetic Data for Model Evaluationcited by 53
  2. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  3. 2021Semi-Supervised Action Recognition with Temporal Contrastive Learningcited by 50
  4. 2021Consistency Regularization for Variational Auto-Encoderscited by 50
  5. 2021Antipodes of Label Differential Privacy: PATE and ALIBIcited by 50
  6. 2022Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detectioncited by 48
  7. 2021Rethinking Pseudo Labels for Semi-Supervised Object Detectioncited by 45
  8. 2021SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Trainingcited by 45
  9. 2023Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspectivecited by 43
  10. 2023Active Teacher for Semi-Supervised Object Detectioncited by 43
  11. 2023CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentationcited by 43
  12. 2021CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learningcited by 41
  13. 2023SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidancecited by 41
  14. 2021A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classificationcited by 36
  15. 2021Revisiting Consistency Regularization for Semi-Supervised Learningcited by 34
  16. 2021Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Trainingcited by 32
  17. 2022BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentationcited by 31
  18. 2021SemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labelingcited by 29
  19. 2023Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentationcited by 29
  20. 2021Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Trainingcited by 28
  21. 2021Test time Adaptation through Perturbation Robustnesscited by 28
  22. 2022Sample Efficiency of Data Augmentation Consistency Regularizationcited by 28
  23. 2021Multimodal Knowledge Expansioncited by 26
  24. 2023Semi-Supervised Domain Adaptation with Source Label Adaptationcited by 26
  25. 2023Boosting Semi-Supervised Learning by Exploiting All Unlabeled Datacited by 26
  26. 2023Balancing Logit Variation for Long-tailed Semantic Segmentationcited by 26
  27. 2022NP-Match: When Neural Processes meet Semi-Supervised Learningcited by 25
  28. 2022ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularizationcited by 25
  29. 2021Semi-Supervised Vision Transformerscited by 24
  30. 2021Exploiting Cross-Modal Prediction and Relation Consistency for Semi-Supervised Image Captioningcited by 23
  31. 2022Bootstrap Motion Forecasting With Self-Consistent Constraintscited by 23
  32. 2023IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilizationcited by 23
  33. 2021Learning Representational Invariances for Data-Efficient Action Recognitioncited by 22
  34. 2022MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularizationcited by 22
  35. 2021Medical Image Segmentation with Limited Supervision: A Review of Deep Network Modelscited by 21
  36. 2021Virtual Augmentation Supported Contrastive Learning of Sentence Representationscited by 21
  37. 2021MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detectioncited by 21
  38. 2021Label-Assemble: Leveraging Multiple Datasets with Partial Labelscited by 20

50 most cited of 241 All 241 (JSON)