mlsanityData to 7 Oct 2026

Hierarchical Variational Memory for Few-shot Learning Across Domains

arXiv 2112.08181 ↗First posted 15 Dec 2021cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Neural memory enables fast adaptation to new tasks with just a few training samples. Existing memory models store features only from the single last layer, which does not generalize well in presence of a domain shift between training and test distributions. Rather than relying on a flat memory, we propose a hierarchical alternative that stores features at different semantic levels. We introduce a hierarchical prototype model, where each level of the prototype fetches corresponding information from the hierarchical memory. The model is endowed with the ability to flexibly rely on features at different semantic levels if the domain shift circumstances so demand. We meta-learn the model by a newly derived hierarchical variational inference framework, where hierarchical memory and prototypes are jointly optimized. To explore and exploit the importance of different semantic levels, we further propose to learn the weights associated with the prototype at each level in a data-driven way, which enables the model to adaptively choose the most generalizable features. We conduct thorough ablation studies to demonstrate the effectiveness of each component in our model. The new state-of-the-art performance on cross-domain and competitive performance on traditional few-shot classification further substantiates the benefit of hierarchical variational memory.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 44 of its 60 references that are in the map. First posted on arXiv 15 Dec 2021.

Builds on

44 of 60 references.

References · 44

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  6. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  7. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  8. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  9. 2016Learning to learn by gradient descent by gradient descentcited by 616
  10. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  11. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  12. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
32 more
  1. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  2. 2018Meta-learning with differentiable closed-form solverscited by 395
  3. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  4. 2014Memory Networkscited by 354
  5. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  6. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  7. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  8. 2017Meta Networkscited by 268
  9. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  10. 2019Cross Attention Network for Few-shot Classificationcited by 218
  11. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 216
  12. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  13. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  14. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  15. 2017Neural Episodic Controlcited by 148
  16. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  17. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  18. 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
  19. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 90
  20. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 75
  21. 2017Learning to Remember Rare Eventscited by 63
  22. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  23. 2017Few-Shot Learning Through an Information Retrieval Lenscited by 51
  24. 2019Metalearned Neural Memorycited by 44
  25. 2020Cross-Domain Few-Shot Learning by Representation Fusioncited by 32
  26. 2021A Bit More Bayesian: Domain-Invariant Learning with Uncertaintycited by 27
  27. 2019Adaptive Posterior Learning: few-shot learning with a surprise-based memory modulecited by 25
  28. 2020Learning to Learn Kernels with Variational Random Featurescited by 18
  29. 2017Variational Memory Addressing in Generative Modelscited by 17
  30. 2020Learning to Learn Variational Semantic Memorycited by 17
  31. 2020Cross-Domain Few-Shot Learning with Meta Fine-Tuningcited by 8
  32. 2021Prototype Completion for Few-Shot Learningcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 7; 2024: 3; 2025: 2.

14 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2023ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusioncited by 15
  3. 2023Energy-Based Test Sample Adaptation for Domain Generalizationcited by 14
  4. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  5. 2024Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Promptingcited by 9
  6. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  7. 2023Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classificationcited by 4
  8. 2023EMO: Episodic Memory Optimization for Few-Shot Meta-Learningcited by 2
  9. 2023One-Shot Learning of Visual Path Navigation for Autonomous Vehiclescited by 1
  10. 2024AdaTreeFormer: Few Shot Domain Adaptation for Tree Counting from a Single High-Resolution Imagecited by 1
  11. 2022Association Graph Learning for Multi-Task Classification with Category Shiftscited by 0
  12. 2023Adaptive Weighted Co-Learning for Cross-Domain Few-Shot Learningcited by 0
2 more
  1. 2025A Cross-Domain Few-Shot Learning Method Based on Domain Knowledge Mappingcited by 0
  2. 2025Variational Task Vector Compositioncited by 0