mlsanityData to 14 Oct 2026

Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn

arXiv 2305.07625 ↗First posted 12 May 2023cs.CV cs.LG stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Meta-learning and other approaches to few-shot learning are widely studied for image recognition, and are increasingly applied to other vision tasks such as pose estimation and dense prediction. This naturally raises the question of whether there is any few-shot meta-learning algorithm capable of generalizing across these diverse task types? To support the community in answering this question, we introduce Meta Omnium, a dataset-of-datasets spanning multiple vision tasks including recognition, keypoint localization, semantic segmentation and regression. We experiment with popular few-shot meta-learning baselines and analyze their ability to generalize across tasks and to transfer knowledge between them. Meta Omnium enables meta-learning researchers to evaluate model generalization to a much wider array of tasks than previously possible, and provides a single framework for evaluating meta-learners across a wide suite of vision applications in a consistent manner.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 58 of its 90 references that are in the map. First posted on arXiv 12 May 2023.

Builds on

58 of 90 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  6. 2016Pyramid Scene Parsing Networkcited by 2,479
  7. 2016Matching Networks for One Shot Learningcited by 2,255
  8. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  9. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  10. 2020In Search of Lost Domain Generalizationcited by 1,054
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  12. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 803
38 more
  1. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 797
  2. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 727
  3. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 699
  4. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  5. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  6. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  7. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  8. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  9. 2019A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmarkcited by 425
  10. 2018Meta-learning with differentiable closed-form solverscited by 397
  11. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  12. 2017One-Shot Learning for Semantic Segmentationcited by 337
  13. 2018Insights on representational similarity in neural networks with canonical correlationcited by 324
  14. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  15. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  16. 2020What Should Not Be Contrastive in Contrastive Learningcited by 226
  17. 2018A System for Massively Parallel Hyperparameter Tuningcited by 202
  18. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
  19. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  20. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  21. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  22. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  23. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  24. 2019Cross-Domain Adaptation for Animal Pose Estimationcited by 108
  25. 2019Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulationcited by 103
  26. 2019Meta-Learning without Memorizationcited by 92
  27. 2021Multi-Task Self-Training for Learning General Representationscited by 85
  28. 2019Meta-Curvaturecited by 70
  29. 2019Learning from Synthetic Animalscited by 65
  30. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  31. 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
  32. 2014A Unified Perspective on Multi-Domain and Multi-Task Learningcited by 33
  33. 2023Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classificationcited by 30
  34. 2021Few-shot Keypoint Detection with Uncertainty Learning for Unseen Speciescited by 27
  35. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  36. 2021Unsupervised Domain Adaptation: A Reality Checkcited by 24
  37. 2021Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learningcited by 22
  38. 2022What Matters For Meta-Learning Vision Regression Tasks?cited by 18

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2.

4 papers.

  1. 2023Meta-learning in healthcare: A surveycited by 9
  2. 2024OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detectioncited by 8
  3. 2023Task-Distributionally Robust Data-Free Meta-Learningcited by 4
  4. 2024UniFS: Universal Few-shot Instance Perception with Point Representationscited by 2