mlsanityData to 7 Oct 2026

Context-Aware Meta-Learning

arXiv 2310.10971 ↗First posted 17 Oct 2023cs.LG cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Large Language Models like ChatGPT demonstrate a remarkable capacity to learn new concepts during inference without any fine-tuning. However, visual models trained to detect new objects during inference have been unable to replicate this ability, and instead either perform poorly or require meta-training and/or fine-tuning on similar objects. In this work, we propose a meta-learning algorithm that emulates Large Language Models by learning new visual concepts during inference without fine-tuning. Our approach leverages a frozen pre-trained feature extractor, and analogous to in-context learning, recasts visual meta-learning as sequence modeling over datapoints with known labels and a test datapoint with an unknown label. On 8 out of 11 meta-learning benchmarks, our approach -- without meta-training or fine-tuning -- exceeds or matches the state-of-the-art algorithm, P>M>F, which is meta-trained on these benchmarks. Our code is available at https://github.com/cfifty/CAML.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 54 of its 81 references that are in the map. First posted on arXiv 17 Oct 2023.

Builds on

54 of 81 references.

References · 54

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  8. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  10. 2016Matching Networks for One Shot Learningcited by 2,246
  11. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  12. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
38 more
  1. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  2. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 713
  3. 2019A Closer Look at Few-shot Classificationcited by 679
  4. 2014Neural Turing Machinescited by 630
  5. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 562
  6. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  7. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  8. 2018Conditional Neural Processescited by 421
  9. 2018Meta-learning with differentiable closed-form solverscited by 395
  10. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  11. 2021Transformers Can Do Bayesian Inferencecited by 338
  12. 2022Images Speak in Images: A Generalist Painter for In-Context Visual Learningcited by 317
  13. 2019A Baseline for Few-Shot Image Classificationcited by 298
  14. 2022Visual Prompting via Image Inpaintingcited by 248
  15. 2015Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Featurecited by 181
  16. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  17. 2023What Makes Good Examples for Visual In-Context Learning?cited by 150
  18. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  19. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  20. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  21. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 112
  22. 2022General-Purpose In-Context Learning by Meta-Learning Transformerscited by 102
  23. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  24. 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
  25. 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
  26. 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 79
  27. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 75
  28. 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 72
  29. 2017Learning to Remember Rare Eventscited by 63
  30. 2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 49
  31. 2020Empirical Bayes Transductive Meta-Learning with Synthetic Gradientscited by 48
  32. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  33. 2023Towards In-context Scene Understandingcited by 45
  34. 2019Self-Supervised Learning For Few-Shot Image Classificationcited by 44
  35. 2022Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficultycited by 37
  36. 2019Few-Shot Learning with Localization in Realistic Settingscited by 34
  37. 2020Enhancing Few-Shot Image Classification with Unlabelled Examplescited by 32
  38. 2023Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matchingcited by 29

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 9; 2026: 2.

20 papers.

Sort:

By area:

  1. 2024Improving Visual Object Tracking through Visual Promptingcited by 9
  2. 2024Making Large Vision Language Models to be Good Few-shot Learnerscited by 7
  3. 2025ECVL-ROUTER: Scenario-Aware Routing for Vision-Language Modelscited by 4
  4. 2024CoLLEGe: Concept Embedding Generation for Large Language Modelscited by 3
  5. 2024Unsupervised Meta-Learning via In-Context Learningcited by 3
  6. 2024Learning to Learn with Contrastive Meta-Objectivecited by 3
  7. 2024Context-Aware Multimodal Pretrainingcited by 3
  8. 2025Flow to Learn: Flow Matching on Neural Network Parameterscited by 3
  9. 2024Cross-Modal Few-Shot Learning: a Generative Transfer Learning Frameworkcited by 2
  10. 2024Tiny models from tiny data: Textual and null-text inversion for few-shot distillationcited by 1
  11. 2025Flows and Diffusions on the Neural Manifoldcited by 1
  12. 2024Using Few-Shot Learning to Classify Primary Lung Cancer and Other Malignancy with Lung Metastasis in Cytological Imaging via Endobronchial Ultrasound Procedurescited by 0
8 more
  1. 2025RoNFA: Robust Neural Field-based Approach for Few-Shot Image Classification with Noisy Labelscited by 0
  2. 2025PictSure: Pretraining Embeddings Matters for In-Context Learning Image Classifierscited by 0
  3. 2025Meta-Learning Transformers to Improve In-Context Generalizationcited by 0
  4. 2025Shallow Deep Learning Can Still Excel in Fine-Grained Few-Shot Learningcited by 0
  5. 2025MetaLab: Few-Shot Game Changer for Image Recognitioncited by 0
  6. 2025Color as the Impetus: Transforming Few-Shot Learnercited by 0
  7. 2026Universal Algorithm-Implicit Learningcited by 0
  8. 2026Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learnerscited by 0