mlsanityData to 7 Oct 2026

Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples

arXiv 1903.03096 ↗First posted 7 Mar 2019cs.LG stat.MLcited by 312

Not on the map. Why?

Abstract (arXiv)

Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and datasets that are used to assess their progress lacking. To address this limitation, we propose Meta-Dataset: a new benchmark for training and evaluating models that is large-scale, consists of diverse datasets, and presents more realistic tasks. We experiment with popular baselines and meta-learners on Meta-Dataset, along with a competitive method that we propose. We analyze performance as a function of various characteristics of test tasks and examine the models' ability to leverage diverse training sources for improving their generalization. We also propose a new set of baselines for quantifying the benefit of meta-learning in Meta-Dataset. Our extensive experimentation has uncovered important research challenges and we hope to inspire work in these directions.

Key facts. Cited by 312 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 86; 2022: 75; 2023: 62; 2024: 50; 2025: 28; 2026: 11.

312 papers.

Sort:

By area:

  1. 2021Transformers in Vision: A Surveycited by 1,009
  2. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  3. 2021Intriguing Properties of Vision Transformerscited by 446
  4. 2021True Few-Shot Learning with Language Modelscited by 343
  5. 2021Few-shot Learning with Multilingual Language Modelscited by 278
  6. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  7. 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
  8. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 141
  9. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  10. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  11. 2021Exploring the Limits of Large Scale Pre-trainingcited by 104
  12. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
38 more
  1. 2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learningcited by 86
  2. 2021Temporal-Relational CrossTransformers for Few-Shot Action Recognitioncited by 83
  3. 2022MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflictscited by 81
  4. 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 79
  5. 2021FLEX: Unifying Evaluation for Few-Shot NLPcited by 67
  6. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  7. 2021Learning a Universal Template for Few-shot Dataset Generalizationcited by 61
  8. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  9. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  10. 2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 49
  11. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  12. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  13. 2023A Closer Look at Few-shot Classification Againcited by 46
  14. 2021Bootstrapped Meta-Learningcited by 45
  15. 2021Orthogonal Projection Losscited by 44
  16. 2021A linearized framework and a new benchmark for model selection for fine-tuningcited by 41
  17. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
  18. 2022Skill-based Meta-Reinforcement Learningcited by 36
  19. 2023Strong Baselines for Parameter Efficient Few-Shot Fine-tuningcited by 36
  20. 2021Few-shot Intent Classification and Slot Filling with Retrieved Examplescited by 35
  21. 2022Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactionscited by 34
  22. 2021Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifiercited by 32
  23. 2021NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Taskscited by 32
  24. 2021A Metalearning Approach for Physics-Informed Neural Networks (PINNs): Application to Parameterized PDEscited by 31
  25. 2024Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuningcited by 31
  26. 2021ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognitioncited by 29
  27. 2021Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalizationcited by 29
  28. 2023Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classificationcited by 29
  29. 2021MetaHTR: Towards Writer-Adaptive Handwritten Text Recognitioncited by 27
  30. 2021Learngene: From Open-World to Your Learning Taskcited by 27
  31. 2022Realistic Evaluation of Transductive Few-Shot Learningcited by 26
  32. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  33. 2021Impact of Aliasing on Generalization in Deep Convolutional Networkscited by 25
  34. 2022Practical Conditional Neural Processes Via Tractable Dependent Predictionscited by 25
  35. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  36. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  37. 2022MetaAudio: A Few-Shot Audio Classification Benchmarkcited by 24
  38. 2023Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Modelscited by 24

50 most cited of 312 All 312 (JSON)