# Learning a Universal Template for Few-shot Dataset Generalization

arXiv: https://arxiv.org/abs/2105.07029 · HTML: https://mlsanity.com/paper/2105.07029/

## Key facts

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

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Learning to Compare: Relation Network for Few-Shot Learning](https://mlsanity.com/paper/1711.06025/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [TADAM: Task dependent adaptive metric for improved few-shot learning](https://mlsanity.com/paper/1805.10123/) (2018)
- [Multi-Task Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2009.09796/) (2020)
- [Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples](https://mlsanity.com/paper/1903.03096/) (2019)
- [Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation](https://mlsanity.com/paper/2001.08735/) (2020)
- [Modulating early visual processing by language](https://mlsanity.com/paper/1707.00683/) (2017)
- [Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes](https://mlsanity.com/paper/1906.07697/) (2019)
- [Improved Few-Shot Visual Classification](https://mlsanity.com/paper/1912.03432/) (2019)
- [Meta-Learning with Warped Gradient Descent](https://mlsanity.com/paper/1909.00025/) (2019)
- [A Universal Representation Transformer Layer for Few-Shot Image Classification](https://mlsanity.com/paper/2006.11702/) (2020)
- [TaskNorm: Rethinking Batch Normalization for Meta-Learning](https://mlsanity.com/paper/2003.03284/) (2020)
- [Scalable Transfer Learning with Expert Models](https://mlsanity.com/paper/2009.13239/) (2020)
- [Universal representations:The missing link between faces, text, planktons, and cat breeds](https://mlsanity.com/paper/1701.07275/) (2017)
- [Optimized Generic Feature Learning for Few-shot Classification across Domains](https://mlsanity.com/paper/2001.07926/) (2020)

## Built on by (most cited first, 30 of 61)

- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference](https://mlsanity.com/paper/2204.07305/) (2022)
- [UniverSeg: Universal Medical Image Segmentation](https://mlsanity.com/paper/2304.06131/) (2023)
- [Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning](https://mlsanity.com/paper/2201.03529/) (2022)
- [Cross-domain Few-shot Learning with Task-specific Adapters](https://mlsanity.com/paper/2107.00358/) (2021)
- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [A Closer Look at Few-shot Classification Again](https://mlsanity.com/paper/2301.12246/) (2023)
- [Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification](https://mlsanity.com/paper/2302.08909/) (2023)
- [Scalable Language Model with Generalized Continual Learning](https://mlsanity.com/paper/2404.07470/) (2024)
- [FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification](https://mlsanity.com/paper/2206.08671/) (2022)
- [Channel Importance Matters in Few-Shot Image Classification](https://mlsanity.com/paper/2206.08126/) (2022)
- [NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research](https://mlsanity.com/paper/2211.11747/) (2022)
- [WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models](https://mlsanity.com/paper/2406.17503/) (2024)
- [Reliable Few-shot Learning under Dual Noises](https://mlsanity.com/paper/2506.16330/) (2025)
- [Few-Shot Adaptation of Pre-Trained Networks for Domain Shift](https://mlsanity.com/paper/2205.15234/) (2022)
- [DETA: Denoised Task Adaptation for Few-Shot Learning](https://mlsanity.com/paper/2303.06315/) (2023)
- [Meta-Learning with a Geometry-Adaptive Preconditioner](https://mlsanity.com/paper/2304.01552/) (2023)
- [Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback](https://mlsanity.com/paper/2309.15762/) (2023)
- [In-Context Learning for Few-Shot Molecular Property Prediction](https://mlsanity.com/paper/2310.08863/) (2023)
- [A Closer Look at Conditional Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2506.23856/) (2025)
- [TIML: Task-Informed Meta-Learning for Agriculture](https://mlsanity.com/paper/2202.02124/) (2022)
- [Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2403.04492/) (2024)
- [RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning](https://mlsanity.com/paper/2303.06679/) (2023)
- [MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation](https://mlsanity.com/paper/2404.19644/) (2024)
- [Towards Few-Shot Learning in the Open World: A Review and Beyond](https://mlsanity.com/paper/2408.09722/) (2024)
- [Enhancing Test Time Adaptation with Few-shot Guidance](https://mlsanity.com/paper/2409.01341/) (2024)
- [Domain Alignment Meets Fully Test-Time Adaptation](https://mlsanity.com/paper/2207.04185/) (2022)
- [CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/2210.09496/) (2022)
- [DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning](https://mlsanity.com/paper/2305.07892/) (2023)

## 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.