mlsanityData to 14 Oct 2026

Multimodality in Meta-Learning: A Comprehensive Survey

arXiv 2109.13576 ↗First posted 28 Sep 2021cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Meta-learning has gained wide popularity as a training framework that is more data-efficient than traditional machine learning methods. However, its generalization ability in complex task distributions, such as multimodal tasks, has not been thoroughly studied. Recently, some studies on multimodality-based meta-learning have emerged. This survey provides a comprehensive overview of the multimodality-based meta-learning landscape in terms of the methodologies and applications. We first formalize the definition of meta-learning in multimodality, along with the research challenges in this growing field, such as how to enrich the input in few-shot learning (FSL) or zero-shot learning (ZSL) in multimodal scenarios and how to generalize the models to new tasks. We then propose a new taxonomy to discuss typical meta-learning algorithms in multimodal tasks systematically. We investigate the contributions of related papers and summarize them by our taxonomy. Finally, we propose potential research directions for this promising field.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 54 of its 94 references that are in the map. First posted on arXiv 28 Sep 2021.

Builds on

54 of 94 references.

References · 54

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  6. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  7. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,013
  8. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  9. 2016Learning to learn by gradient descent by gradient descentcited by 620
  10. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  11. 2014Deep metric learning using Triplet networkcited by 422
  12. 2017Few-Shot Learning with Graph Neural Networkscited by 324
38 more
  1. 2017Data Augmentation Generative Adversarial Networkscited by 278
  2. 2017Recent Trends in Deep Learning Based Natural Language Processingcited by 263
  3. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  4. 2018Meta-Learning: A Surveycited by 256
  5. 2021SMIL: Multimodal Learning with Severely Missing Modalitycited by 245
  6. 2016Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Groundingcited by 243
  7. 2018Low-Shot Learning from Imaginary Datacited by 181
  8. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  9. 2019Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulationcited by 103
  10. 2020A Survey of Deep Meta-Learningcited by 100
  11. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  12. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
  13. 2019Generalized Inner Loop Meta-Learningcited by 93
  14. 2019Multimodal Transformer with Multi-View Visual Representation for Image Captioningcited by 86
  15. 2021Graph-based Semi-supervised Learning: A Comprehensive Reviewcited by 79
  16. 2018Unsupervised Meta-Learning For Few-Shot Image Classificationcited by 75
  17. 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
  18. 2019Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Predictioncited by 64
  19. 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
  20. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  21. 2020Improving Generalization in Meta-learning via Task Augmentationcited by 55
  22. 2020Multimodal Prototypical Networks for Few-shot Learningcited by 48
  23. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  24. 2020Meta-learning for Few-shot Natural Language Processing: A Surveycited by 42
  25. 2019Baby steps towards few-shot learning with multiple semanticscited by 29
  26. 2019Shaping Visual Representations with Language for Few-shot Classificationcited by 27
  27. 2020AutoGraph: Automated Graph Neural Networkcited by 21
  28. 2021Task Aligned Generative Meta-learning for Zero-shot Learningcited by 19
  29. 2020Task Augmentation by Rotating for Meta-Learningcited by 18
  30. 2020Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignmentcited by 16
  31. 2020A Comprehensive Overview and Survey of Recent Advances in Meta-Learningcited by 15
  32. 2019Towards Understanding Generalization in Gradient-Based Meta-Learningcited by 12
  33. 2018Multimodal One-Shot Learning of Speech and Imagescited by 11
  34. 2017Improving One-Shot Learning through Fusing Side Informationcited by 10
  35. 2018Self Paced Adversarial Training for Multimodal Few-shot Learningcited by 8
  36. 2021HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalitiescited by 8
  37. 2020Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learningcited by 6
  38. 2020Direct multimodal few-shot learning of speech and imagescited by 6

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 5; 2024: 1; 2025: 2.

11 papers.

  1. 2023MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognitioncited by 26
  2. 2023Enhancing Modality-Agnostic Representations via Meta-Learning for Brain Tumor Segmentationcited by 14
  3. 2022Federated Learning and Meta Learning: Approaches, Applications, and Directionscited by 12
  4. 2021Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta reviewcited by 6
  5. 2025CAMeL: Cross-modality Adaptive Meta-Learning for Text-based Person Retrievalcited by 6
  6. 2023MetaViewer: Towards A Unified Multi-View Representationcited by 5
  7. 2025Generalization-Enhanced Few-Shot Object Detection in Remote Sensingcited by 4
  8. 2023Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworkscited by 2
  9. 2023HyperCoil-Recon: A Hypernetwork-based Adaptive Coil Configuration Task Switching Network for MRI Reconstructioncited by 2
  10. 2024Patch-based Intuitive Multimodal Prototypes Network (PIMPNet) for Alzheimer's Disease classificationcited by 2
  11. 2022Multi-Modal Fusion by Meta-Initializationcited by 0