mlsanityData to 7 Oct 2026

The Omniglot challenge: a 3-year progress report

arXiv 1902.03477 ↗First posted 9 Feb 2019cs.AI cs.CV cs.LGcited by 54

Not on the map. Why?

Abstract (arXiv)

Three years ago, we released the Omniglot dataset for one-shot learning, along with five challenge tasks and a computational model that addresses these tasks. The model was not meant to be the final word on Omniglot; we hoped that the community would build on our work and develop new approaches. In the time since, we have been pleased to see wide adoption of the dataset. There has been notable progress on one-shot classification, but researchers have adopted new splits and procedures that make the task easier. There has been less progress on the other four tasks. We conclude that recent approaches are still far from human-like concept learning on Omniglot, a challenge that requires performing many tasks with a single model.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 10; 2023: 16; 2024: 14; 2025: 0; 2026: 4.

54 papers.

Sort:

By area:

  1. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  2. 2022Data Distributional Properties Drive Emergent In-Context Learning in Transformerscited by 303
  3. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  4. 2023The mechanistic basis of data dependence and abrupt learning in an in-context classification taskcited by 115
  5. 2021Opening up Open-World Trackingcited by 50
  6. 2023MEWL: Few-shot multimodal word learning with referential uncertaintycited by 17
  7. 2023Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approachcited by 17
  8. 2023Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Abilitycited by 16
  9. 2024Frozen Feature Augmentation for Few-Shot Image Classificationcited by 13
  10. 2023Towards Task Sampler Learning for Meta-Learningcited by 11
  11. 2023Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?cited by 10
  12. 2024Anchor function: a type of benchmark functions for studying language modelscited by 10
38 more
  1. 2022Interactive Visual Reasoning under Uncertaintycited by 8
  2. 2023Hacking Task Confounder in Meta-Learningcited by 8
  3. 2023Compositional diversity in visual concept learningcited by 7
  4. 2021Set-to-Sequence Methods in Machine Learning: a Reviewcited by 6
  5. 2022Drawing out of Distribution with Neuro-Symbolic Generative Modelscited by 5
  6. 2024On-device Online Learning and Semantic Management of TinyML Systemscited by 5
  7. 2026Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformerscited by 5
  8. 2022Learning from One and Only One Shotcited by 4
  9. 2022Adaptive Prototypical Networkscited by 4
  10. 2023A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniquescited by 4
  11. 2023TinyReptile: TinyML with Federated Meta-Learningcited by 4
  12. 2021Meta-learning of Pooling Layers for Character Recognitioncited by 3
  13. 2024Latent Representation Matters: Human-like Sketches in One-shot Drawing Taskscited by 3
  14. 2021Embedding Adaptation is Still Needed for Few-Shot Learningcited by 2
  15. 2022Offline Handwritten Amharic Character Recognition Using Few-shot Learningcited by 2
  16. 2023Guided Transfer Learningcited by 2
  17. 2023Meta-Learning in Spiking Neural Networks with Reward-Modulated STDPcited by 2
  18. 2023Unleash Model Potential: Bootstrapped Meta Self-supervised Learningcited by 2
  19. 2024Learning to Infer Generative Template Programs for Visual Conceptscited by 2
  20. 2024GCV-Turbo: End-to-end Acceleration of GNN-based Computer Vision Tasks on FPGAcited by 2
  21. 2024Bayesian Inverse Graphics for Few-Shot Concept Learningcited by 2
  22. 2021One-shot learning for the long term: consolidation with an artificial hippocampal algorithmcited by 1
  23. 2021Learning from the Tangram to Solve Mini Visual Taskscited by 1
  24. 2022Fast Learning of Dynamic Hand Gesture Recognition with Few-Shot Learning Modelscited by 1
  25. 2023Computing with Categories in Machine Learningcited by 1
  26. 2023Advancing Counterfactual Inference through Nonlinear Quantile Regressioncited by 1
  27. 2024On the Universality of Self-Supervised Learningcited by 1
  28. 2024Rethinking Meta-Learning from a Learning Lenscited by 1
  29. 2024BelHouse3D: A Benchmark Dataset for Assessing Occlusion Robustness in 3D Point Cloud Semantic Segmentationcited by 1
  30. 2026Contrastive-to-Self-Supervised: A Two-Stage Framework for Script Similarity Learningcited by 1
  31. 2021Prototypical Region Proposal Networks for Few-Shot Localization and Classificationcited by 0
  32. 2021A Relational Model for One-Shot Classificationcited by 0
  33. 2021Meta-Learning and Self-Supervised Pretraining for Real World Image Translationcited by 0
  34. 2022Distributed Evolution Strategies Using TPUs for Meta-Learningcited by 0
  35. 2022A Probabilistic Generative Model of Free Categoriescited by 0
  36. 2023ViewMix: Augmentation for Robust Representation in Self-Supervised Learningcited by 0
  37. 2024Guided Sketch-Based Program Induction by Search Gradientscited by 0
  38. 2024Non-negative Subspace Feature Representation for Few-shot Learning in Medical Imagingcited by 0

50 most cited of 54 All 54 (JSON)