mlsanityData to 7 Oct 2026

Meta Pseudo Labels

arXiv 2003.10580 ↗First posted 23 Mar 2020cs.LG stat.MLcited by 372

Not on the map. Why?

Abstract (arXiv)

We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art. Like Pseudo Labels, Meta Pseudo Labels has a teacher network to generate pseudo labels on unlabeled data to teach a student network. However, unlike Pseudo Labels where the teacher is fixed, the teacher in Meta Pseudo Labels is constantly adapted by the feedback of the student's performance on the labeled dataset. As a result, the teacher generates better pseudo labels to teach the student. Our code will be available at https://github.com/google-research/google-research/tree/master/meta_pseudo_labels.

Key facts. Cited by 372 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 89; 2022: 96; 2023: 87; 2024: 51; 2025: 37; 2026: 12.

372 papers.

Sort:

By area:

  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  2. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  3. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  4. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,265
  5. 2021Scaling Vision Transformerscited by 993
  6. 2021Going deeper with Image Transformerscited by 759
  7. 2021Scaling Vision with Sparse Mixture of Expertscited by 740
  8. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  9. 2021RegionCLIP: Region-based Language-Image Pretrainingcited by 612
  10. 2021Extract Free Dense Labels from CLIPcited by 580
  11. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 359
  12. 2022Is synthetic data from generative models ready for image recognition?cited by 320
38 more
  1. 2022MultiMAE: Multi-modal Multi-task Masked Autoencoderscited by 287
  2. 2021A Survey on Deep Semi-supervised Learningcited by 250
  3. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  4. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  5. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  6. 2021Combined Scaling for Zero-shot Transfer Learningcited by 182
  7. 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 177
  8. 2022Compute Trends Across Three Eras of Machine Learningcited by 161
  9. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
  10. 2021Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalizationcited by 141
  11. 2021Efficient Sharpness-aware Minimization for Improved Training of Neural Networkscited by 137
  12. 2023SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learningcited by 133
  13. 2022ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyondcited by 117
  14. 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
  15. 2021Mutual Consistency Learning for Semi-supervised Medical Image Segmentationcited by 107
  16. 2021Exploring the Limits of Large Scale Pre-trainingcited by 104
  17. 2024Self-Improvement in Language Models: The Sharpening Mechanismcited by 102
  18. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
  19. 2022Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentationcited by 93
  20. 2023DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusioncited by 85
  21. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  22. 2021Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognitioncited by 71
  23. 2021Learning Fast Sample Re-weighting Without Reward Datacited by 69
  24. 2022Music Source Separation with Band-split RNNcited by 69
  25. 2022Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?cited by 67
  26. 2021Are we ready for a new paradigm shift? A Survey on Visual Deep MLPcited by 63
  27. 2022Debiased Self-Training for Semi-Supervised Learningcited by 62
  28. 2021BERT Learns to Teach: Knowledge Distillation with Meta Learningcited by 61
  29. 2021A Closer Look at Self-training for Zero-Label Semantic Segmentationcited by 57
  30. 2021No One Representation to Rule Them All: Overlapping Features of Training Methodscited by 57
  31. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  32. 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 53
  33. 2021GANav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environmentscited by 51
  34. 2021DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learningcited by 51
  35. 2021E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognitioncited by 50
  36. 2021Instance-Dependent Partial Label Learningcited by 49
  37. 2022Semi-supervised Vision Transformers at Scalecited by 49
  38. 2023STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tablescited by 48

50 most cited of 372 All 372 (JSON)