mlsanityData to 7 Oct 2026

Learning a Universal Template for Few-shot Dataset Generalization

arXiv 2105.07029 ↗First posted 14 May 2021cs.LG cs.CVcited by 61

Not on the map. Why?

Abstract (arXiv)

Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from new datasets using only a few examples. To this end, we propose to utilize the diverse training set to construct a universal template: a partial model that can define a wide array of dataset-specialized models, by plugging in appropriate components. For each new few-shot classification problem, our approach therefore only requires inferring a small number of parameters to insert into the universal template. We design a separate network that produces an initialization of those parameters for each given task, and we then fine-tune its proposed initialization via a few steps of gradient descent. Our approach is more parameter-efficient, scalable and adaptable compared to previous methods, and achieves the state-of-the-art on the challenging Meta-Dataset benchmark.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 14 May 2021.

Builds on

24 of 36 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  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. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  5. 2016Matching Networks for One Shot Learningcited by 2,246
  6. 2017Deep Setscited by 1,394
  7. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  8. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  9. 2020In Search of Lost Domain Generalizationcited by 1,042
  10. 2019A Closer Look at Few-shot Classificationcited by 679
  11. 2017Learning multiple visual domains with residual adapterscited by 553
  12. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
12 more
  1. 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 374
  2. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  3. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  4. 2017Modulating early visual processing by languagecited by 167
  5. 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
  6. 2019Improved Few-Shot Visual Classificationcited by 114
  7. 2019Meta-Learning with Warped Gradient Descentcited by 98
  8. 2020A Universal Representation Transformer Layer for Few-Shot Image Classificationcited by 65
  9. 2020TaskNorm: Rethinking Batch Normalization for Meta-Learningcited by 50
  10. 2020Scalable Transfer Learning with Expert Modelscited by 48
  11. 2017Universal representations:The missing link between faces, text, planktons, and cat breedscited by 45
  12. 2020Optimized Generic Feature Learning for Few-shot Classification across Domainscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 18; 2023: 20; 2024: 12; 2025: 7; 2026: 2.

61 papers.

Sort:

By area:

  1. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  2. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  3. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  4. 2023UniverSeg: Universal Medical Image Segmentationcited by 90
  5. 2022Head2Toe: Utilizing Intermediate Representations for Better Transfer Learningcited by 83
  6. 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 79
  7. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  8. 2023A Closer Look at Few-shot Classification Againcited by 46
  9. 2023Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classificationcited by 29
  10. 2024Scalable Language Model with Generalized Continual Learningcited by 28
  11. 2022FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classificationcited by 26
  12. 2022Channel Importance Matters in Few-Shot Image Classificationcited by 20
38 more
  1. 2022NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Researchcited by 18
  2. 2022Few-Shot Adaptation of Pre-Trained Networks for Domain Shiftcited by 16
  3. 2024WAVE: Weight Templates for Adaptive Initialization of Variable-sized Modelscited by 16
  4. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  5. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  6. 2023Meta-Learning with a Geometry-Adaptive Preconditionercited by 11
  7. 2023Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedbackcited by 10
  8. 2022TIML: Task-Informed Meta-Learning for Agriculturecited by 7
  9. 2023In-Context Learning for Few-Shot Molecular Property Predictioncited by 7
  10. 2024Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learningcited by 7
  11. 2025A Closer Look at Conditional Prompt Tuning for Vision-Language Modelscited by 7
  12. 2023RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learningcited by 5
  13. 2024MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlationcited by 5
  14. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  15. 2024Enhancing Test Time Adaptation with Few-shot Guidancecited by 5
  16. 2022Domain Alignment Meets Fully Test-Time Adaptationcited by 4
  17. 2022CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrationscited by 4
  18. 2023DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learningcited by 4
  19. 2023Neural Fine-Tuning Search for Few-Shot Learningcited by 4
  20. 2023SINC: Self-Supervised In-Context Learning for Vision-Language Taskscited by 4
  21. 2024MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependencecited by 4
  22. 2022NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline resultscited by 3
  23. 2023Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classificationcited by 3
  24. 2023Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learningcited by 3
  25. 2024Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Expertscited by 3
  26. 2024Mind the Gap Between Prototypes and Images in Cross-domain Finetuningcited by 3
  27. 2024Context-Aware Multimodal Pretrainingcited by 3
  28. 2021Identifying and Benchmarking Natural Out-of-Context Prediction Problemscited by 2
  29. 2022Feature Extractor Stacking for Cross-domain Few-shot Learningcited by 2
  30. 2022Robust Meta-Representation Learning via Global Label Inference and Classificationcited by 2
  31. 2024EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logitscited by 2
  32. 2025Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspectivecited by 2
  33. 2022How to Train an Accurate and Efficient Object Detection Model on Any Datasetcited by 1
  34. 2023Improving the Generalizability of Collaborative Dialogue Analysis with Multi-Feature Embeddingscited by 1
  35. 2023SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarizationcited by 1
  36. 2023Towards Domain-Specific Features Disentanglement for Domain Generalizationcited by 1
  37. 2023Subspace Adaptation Prior for Few-Shot Learningcited by 1
  38. 2022Unidirectional Thin Adapter for Efficient Adaptation of Deep Neural Networkscited by 0

50 most cited of 61 All 61 (JSON)