# Learning feed-forward one-shot learners

arXiv: https://arxiv.org/abs/1606.05233 · HTML: https://mlsanity.com/paper/1606.05233/

## Key facts

- Cited by 93 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2016.

## Built on by (most cited first, 30 of 93)

- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Prompting Decision Transformer for Few-Shot Policy Generalization](https://mlsanity.com/paper/2206.13499/) (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)
- [Parameter Prediction for Unseen Deep Architectures](https://mlsanity.com/paper/2110.13100/) (2021)
- [Modular Deep Learning](https://mlsanity.com/paper/2302.11529/) (2023)
- [Cross-domain Few-shot Learning with Task-specific Adapters](https://mlsanity.com/paper/2107.00358/) (2021)
- [Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights](https://mlsanity.com/paper/2209.14733/) (2022)
- [Learning Dynamic Alignment via Meta-filter for Few-shot Learning](https://mlsanity.com/paper/2103.13582/) (2021)
- [MoStGAN-V: Video Generation with Temporal Motion Styles](https://mlsanity.com/paper/2304.02777/) (2023)
- [Learning Optical Flow with Adaptive Graph Reasoning](https://mlsanity.com/paper/2202.03857/) (2022)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection](https://mlsanity.com/paper/2203.13903/) (2022)
- [Open Long-Tailed Recognition in a Dynamic World](https://mlsanity.com/paper/2208.08349/) (2022)
- [Embedding in Recommender Systems: A Survey](https://mlsanity.com/paper/2310.18608/) (2023)
- [Pareto Set Learning for Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2501.06773/) (2025)
- [HyperINR: A Fast and Predictive Hypernetwork for Implicit Neural Representations via Knowledge Distillation](https://mlsanity.com/paper/2304.04188/) (2023)
- [MotherNet: Fast Training and Inference via Hyper-Network Transformers](https://mlsanity.com/paper/2312.08598/) (2023)
- [Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling](https://mlsanity.com/paper/2201.06814/) (2022)
- [Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting](https://mlsanity.com/paper/2405.10800/) (2024)
- [Few-Shot Learning with a Strong Teacher](https://mlsanity.com/paper/2107.00197/) (2021)
- [Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey](https://mlsanity.com/paper/2303.08557/) (2023)
- [CVAE-H: Conditionalizing Variational Autoencoders via Hypernetworks and Trajectory Forecasting for Autonomous Driving](https://mlsanity.com/paper/2201.09874/) (2022)
- [SiamMask: A Framework for Fast Online Object Tracking and Segmentation](https://mlsanity.com/paper/2207.02088/) (2022)
- [Focus Your Attention (with Adaptive IIR Filters)](https://mlsanity.com/paper/2305.14952/) (2023)
- [When Meta-Learning Meets Online and Continual Learning: A Survey](https://mlsanity.com/paper/2311.05241/) (2023)
- [Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysis](https://mlsanity.com/paper/2205.04281/) (2022)
- [SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders](https://mlsanity.com/paper/2304.06914/) (2023)

## Abstract (arXiv)

One-shot learning is usually tackled by using generative models or discriminative embeddings. Discriminative methods based on deep learning, which are very effective in other learning scenarios, are ill-suited for one-shot learning as they need large amounts of training data. In this paper, we propose a method to learn the parameters of a deep model in one shot. We construct the learner as a second deep network, called a learnet, which predicts the parameters of a pupil network from a single exemplar. In this manner we obtain an efficient feed-forward one-shot learner, trained end-to-end by minimizing a one-shot classification objective in a learning to learn formulation. In order to make the construction feasible, we propose a number of factorizations of the parameters of the pupil network. We demonstrate encouraging results by learning characters from single exemplars in Omniglot, and by tracking visual objects from a single initial exemplar in the Visual Object Tracking benchmark.