mlsanityData to 7 Oct 2026

Learning feed-forward one-shot learners

arXiv 1606.05233 ↗First posted 16 Jun 2016cs.CV cs.LGcited by 93

Not on the map. Why?

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.

Key facts. Cited by 93 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 23; 2022: 29; 2023: 17; 2024: 11; 2025: 7; 2026: 5.

93 papers.

Sort:

By area:

  1. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  2. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  3. 2021Dynamic Neural Networks: A Surveycited by 405
  4. 2022Prompting Decision Transformer for Few-Shot Policy Generalizationcited by 143
  5. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  6. 2021Parameter Prediction for Unseen Deep Architecturescited by 89
  7. 2023Modular Deep Learningcited by 82
  8. 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 79
  9. 2022Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weightscited by 63
  10. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  11. 2023MoStGAN-V: Video Generation with Temporal Motion Stylescited by 37
  12. 2022Learning Optical Flow with Adaptive Graph Reasoningcited by 33
38 more
  1. 2023Learning Conditional Attributes for Compositional Zero-Shot Learningcited by 28
  2. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  3. 2022Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detectioncited by 23
  4. 2022Open Long-Tailed Recognition in a Dynamic Worldcited by 21
  5. 2023HyperINR: A Fast and Predictive Hypernetwork for Implicit Neural Representations via Knowledge Distillationcited by 19
  6. 2023Embedding in Recommender Systems: A Surveycited by 19
  7. 2023MotherNet: Fast Training and Inference via Hyper-Network Transformerscited by 19
  8. 2022Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modelingcited by 18
  9. 2024Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecastingcited by 18
  10. 2025Pareto Set Learning for Multi-Objective Reinforcement Learningcited by 18
  11. 2021Few-Shot Learning with a Strong Teachercited by 16
  12. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  13. 2022CVAE-H: Conditionalizing Variational Autoencoders via Hypernetworks and Trajectory Forecasting for Autonomous Drivingcited by 13
  14. 2022SiamMask: A Framework for Fast Online Object Tracking and Segmentationcited by 13
  15. 2023Focus Your Attention (with Adaptive IIR Filters)cited by 12
  16. 2023When Meta-Learning Meets Online and Continual Learning: A Surveycited by 12
  17. 2022Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysiscited by 11
  18. 2023SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoderscited by 11
  19. 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
  20. 2023Graph Sampling-based Meta-Learning for Molecular Property Predictioncited by 10
  21. 2022OCD: Learning to Overfit with Conditional Diffusion Modelscited by 9
  22. 2022Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworkscited by 8
  23. 2022Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparisoncited by 8
  24. 2021On the Importance of Firth Bias Reduction in Few-Shot Classificationcited by 7
  25. 2021Meta Internal Learningcited by 7
  26. 2021MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samplescited by 6
  27. 2022MetaTPTrans: A Meta Learning Approach for Multilingual Code Representation Learningcited by 6
  28. 2022tSF: Transformer-based Semantic Filter for Few-Shot Learningcited by 6
  29. 2024No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representationscited by 5
  30. 2025Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigationcited by 5
  31. 2021Transferring Unconditional to Conditional GANs with Hyper-Modulationcited by 4
  32. 2021Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learningcited by 4
  33. 2023SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learningcited by 4
  34. 2023Meta-DM: Applications of Diffusion Models on Few-Shot Learningcited by 4
  35. 2025Practical Continual Forgetting for Pre-trained Vision Modelscited by 4
  36. 2021Risk Prediction on Traffic Accidents using a Compact Neural Model for Multimodal Information Fusion over Urban Big Datacited by 3
  37. 2021Contextual HyperNetworks for Novel Feature Adaptationcited by 3
  38. 2021AutoTransfer: Subject Transfer Learning with Censored Representations on Biosignals Datacited by 3

50 most cited of 93 All 93 (JSON)