mlsanityData to 7 Oct 2026

Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition

arXiv 2101.02833 ↗First posted 8 Jan 2021cs.LGcited by 48

Not on the map. Why?

Abstract (arXiv)

Current state-of-the-art few-shot learners focus on developing effective training procedures for feature representations, before using simple, e.g. nearest centroid, classifiers. In this paper, we take an orthogonal approach that is agnostic to the features used and focus exclusively on meta-learning the actual classifier layer. Specifically, we introduce MetaQDA, a Bayesian meta-learning generalization of the classic quadratic discriminant analysis. This setup has several benefits of interest to practitioners: meta-learning is fast and memory-efficient, without the need to fine-tune features. It is agnostic to the off-the-shelf features chosen and thus will continue to benefit from advances in feature representations. Empirically, it leads to robust performance in cross-domain few-shot learning and, crucially for real-world applications, it leads to better uncertainty calibration in predictions.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 50 of its 70 references that are in the map. First posted on arXiv 8 Jan 2021.

Builds on

50 of 70 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2014How transferable are features in deep neural networks?cited by 1,216
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  11. 2019A Closer Look at Few-shot Classificationcited by 679
  12. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
38 more
  1. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  2. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  3. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  4. 2019Measuring Calibration in Deep Learningcited by 443
  5. 2018Conditional Neural Processescited by 421
  6. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  7. 2018Meta-learning with differentiable closed-form solverscited by 395
  8. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  9. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  10. 2017A simple neural network module for relational reasoningcited by 345
  11. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  12. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  13. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  14. 2020Few-Shot Class-Incremental Learningcited by 249
  15. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  16. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  17. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  18. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  19. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  20. 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
  21. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  22. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  23. 2019Improved Few-Shot Visual Classificationcited by 114
  24. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  25. 2018Meta-Learning Probabilistic Inference For Predictioncited by 108
  26. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
  27. 2019Meta-Learning without Memorizationcited by 92
  28. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 90
  29. 2019AI Benchmark: All About Deep Learning on Smartphones in 2019cited by 76
  30. 2019Diversity with Cooperation: Ensemble Methods for Few-Shot Classificationcited by 70
  31. 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 65
  32. 2020A Universal Representation Transformer Layer for Few-Shot Image Classificationcited by 65
  33. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  34. 2020Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Taskscited by 47
  35. 2019Few-Shot Learning with Global Class Representationscited by 44
  36. 2018Few-Shot Learning with Metric-Agnostic Conditional Embeddingscited by 40
  37. 2018Toward Scalable Verification for Safety-Critical Deep Networkscited by 12
  38. 2018RelationNet2: Deep Comparison Columns for Few-Shot Learningcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 13; 2023: 12; 2024: 14; 2025: 5.

48 papers.

Sort:

By area:

  1. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  2. 2024Variational Bayesian Last Layerscited by 67
  3. 2023MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learningcited by 40
  4. 2022Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofingcited by 38
  5. 2024Diffusion-Based Neural Network Weights Generationcited by 38
  6. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  7. 2022SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Modelscited by 34
  8. 2022Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learningcited by 27
  9. 2022Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learningcited by 23
  10. 2023Supervised Masked Knowledge Distillation for Few-Shot Transformerscited by 23
  11. 2022Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignmentscited by 22
  12. 2023Context-Aware Meta-Learningcited by 20
36 more
  1. 2023TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edgecited by 18
  2. 2024A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trendscited by 16
  3. 2023Towards Task Sampler Learning for Meta-Learningcited by 11
  4. 2023On the Importance of Spatial Relations for Few-shot Action Recognitioncited by 11
  5. 2022Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classificationcited by 10
  6. 2021On the Importance of Firth Bias Reduction in Few-Shot Classificationcited by 7
  7. 2022Transductive Decoupled Variational Inference for Few-Shot Classificationcited by 7
  8. 2024BECLR: Batch Enhanced Contrastive Few-Shot Learningcited by 6
  9. 2022Self-Attention Message Passing for Contrastive Few-Shot Learningcited by 4
  10. 2022Enhancing Few-shot Image Classification with Cosine Transformercited by 4
  11. 2023Meta-DM: Applications of Diffusion Models on Few-Shot Learningcited by 4
  12. 2024CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusioncited by 4
  13. 2021Gaussian Process Meta Few-shot Classifier Learning via Linear Discriminant Laplace Approximationcited by 3
  14. 2023Unleash Model Potential: Bootstrapped Meta Self-supervised Learningcited by 2
  15. 2021How Sensitive are Meta-Learners to Dataset Imbalance?cited by 1
  16. 2022Bayesian Evidential Learning for Few-Shot Classificationcited by 1
  17. 2022BaseTransformers: Attention over base data-points for One Shot Learningcited by 1
  18. 2023Exploring Active Learning in Meta-Learning: Enhancing Context Set Labelingcited by 1
  19. 2024On the Universality of Self-Supervised Learningcited by 1
  20. 2024Intra-task Mutual Attention based Vision Transformer for Few-Shot Learningcited by 1
  21. 2024Class-relevant Patch Embedding Selection for Few-Shot Image Classificationcited by 1
  22. 2024Tiny models from tiny data: Textual and null-text inversion for few-shot distillationcited by 1
  23. 2025Slot Attention-based Feature Filtering for Few-Shot Learningcited by 1
  24. 2021Meta-learning Amidst Heterogeneity and Ambiguitycited by 0
  25. 2023AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design Anywherecited by 0
  26. 2023A Hierarchical Bayesian Model for Deep Few-Shot Meta Learningcited by 0
  27. 2023Few-shot Image Classification based on Gradual Machine Learningcited by 0
  28. 2024Like Humans to Few-Shot Learning through Knowledge Permeation of Vision and Textcited by 0
  29. 2024Bayesian meta learning for trustworthy uncertainty quantificationcited by 0
  30. 2024Siamese Transformer Networks for Few-shot Image Classificationcited by 0
  31. 2024A Simple Task-aware Contrastive Local Descriptor Selection Strategy for Few-shot Learning between inter class and intra classcited by 0
  32. 2024Neuromodulated Meta-Learningcited by 0
  33. 2025Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classificationcited by 0
  34. 2025UBMF: Uncertainty-Aware Bayesian Meta-Learning Framework for Fault Diagnosis with Imbalanced Industrial Datacited by 0
  35. 2025RoNFA: Robust Neural Field-based Approach for Few-Shot Image Classification with Noisy Labelscited by 0
  36. 2025Color as the Impetus: Transforming Few-Shot Learnercited by 0