mlsanityData to 14 Oct 2026

Meta Networks

arXiv 1703.00837 ↗First posted 2 Mar 2017cs.LG stat.MLcited by 269

Not on the map. Why?

Abstract (arXiv)

Neural networks have been successfully applied in applications with a large amount of labeled data. However, the task of rapid generalization on new concepts with small training data while preserving performances on previously learned ones still presents a significant challenge to neural network models. In this work, we introduce a novel meta learning method, Meta Networks (MetaNet), that learns a meta-level knowledge across tasks and shifts its inductive biases via fast parameterization for rapid generalization. When evaluated on Omniglot and Mini-ImageNet benchmarks, our MetaNet models achieve a near human-level performance and outperform the baseline approaches by up to 6% accuracy. We demonstrate several appealing properties of MetaNet relating to generalization and continual learning.

Key facts. Cited by 269 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 94; 2022: 63; 2023: 54; 2024: 30; 2025: 18; 2026: 9.

269 papers.

Sort:

By area:

  1. 2021Linear Transformers Are Secretly Fast Weight Programmerscited by 502
  2. 2024Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attentioncited by 200
  3. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 153
  4. 2021DEMix Layers: Disentangling Domains for Modular Language Modelingcited by 132
  5. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  6. 2023FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learningcited by 87
  7. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  8. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  9. 2021Learning Normal Dynamics in Videos with Meta Prototype Networkcited by 71
  10. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  11. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  12. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 58
38 more
  1. 2022Transferability in Deep Learning: A Surveycited by 57
  2. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  3. 2022Omni-Dimensional Dynamic Convolutioncited by 55
  4. 2021Multiple Meta-model Quantifying for Medical Visual Question Answeringcited by 54
  5. 2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
  6. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  7. 2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variablescited by 50
  8. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  9. 2023A Survey on Few-Shot Class-Incremental Learningcited by 48
  10. 2023A Closer Look at Few-shot Classification Againcited by 46
  11. 2022Hypernetworks in Meta-Reinforcement Learningcited by 42
  12. 2022A Modern Self-Referential Weight Matrix That Learns to Modify Itselfcited by 41
  13. 2024Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Conceptscited by 40
  14. 2021Meta-Learning Dynamics Forecasting Using Task Inferencecited by 38
  15. 2022Learning Domain Invariant Prompt for Vision-Language Modelscited by 36
  16. 2021A Metalearning Approach for Physics-Informed Neural Networks (PINNs): Application to Parameterized PDEscited by 32
  17. 2021On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learningcited by 29
  18. 2021Learning Implicit Temporal Alignment for Few-shot Video Classificationcited by 27
  19. 2024Prompt Learning via Meta-Regularizationcited by 26
  20. 2021Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognitioncited by 25
  21. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  22. 2026SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Passcited by 25
  23. 2021RF-Net: a Unified Meta-learning Framework for RF-enabled One-shot Human Activity Recognitioncited by 24
  24. 2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
  25. 2023Context-enriched molecule representations improve few-shot drug discoverycited by 24
  26. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  27. 2022Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learningcited by 23
  28. 2022Few-shot Learning with Noisy Labelscited by 23
  29. 2022Deep Learning and Symbolic Regression for Discovering Parametric Equationscited by 23
  30. 2021Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learningcited by 22
  31. 2022Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learningcited by 22
  32. 2022Open Long-Tailed Recognition in a Dynamic Worldcited by 21
  33. 2022Meta-Learning Fast Weight Language Modelscited by 21
  34. 2023Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Modelscited by 21
  35. 2022FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relationscited by 20
  36. 2022FHIST: A Benchmark for Few-shot Classification of Histological Imagescited by 20
  37. 2023Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learningcited by 20
  38. 2022Attribute Prototype Network for Any-Shot Learningcited by 19

50 most cited of 269 All 269 (JSON)