mlsanityData to 7 Oct 2026

Bayesian Embeddings for Few-Shot Open World Recognition

arXiv 2107.13682 ↗First posted 29 Jul 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

As autonomous decision-making agents move from narrow operating environments to unstructured worlds, learning systems must move from a closed-world formulation to an open-world and few-shot setting in which agents continuously learn new classes from small amounts of information. This stands in stark contrast to modern machine learning systems that are typically designed with a known set of classes and a large number of examples for each class. In this work we extend embedding-based few-shot learning algorithms to the open-world recognition setting. We combine Bayesian non-parametric class priors with an embedding-based pre-training scheme to yield a highly flexible framework which we refer to as few-shot learning for open world recognition (FLOWR). We benchmark our framework on open-world extensions of the common MiniImageNet and TieredImageNet few-shot learning datasets. Our results show, compared to prior methods, strong classification accuracy performance and up to a 12% improvement in H-measure (a measure of novel class detection) from our non-parametric open-world few-shot learning scheme.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 58 references that are in the map. First posted on arXiv 29 Jul 2021.

Builds on

31 of 58 references.

References · 31

  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. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  8. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  9. 2018End-to-End Incremental Learningcited by 596
  10. 2015Towards Open Set Deep Networkscited by 533
  11. 2019Meta-Learning with Implicit Gradientscited by 523
  12. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
19 more
  1. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  2. 2018Meta-learning with differentiable closed-form solverscited by 395
  3. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  4. 2019Orthogonal Gradient Descent for Continual Learningcited by 361
  5. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  6. 2018Recent Advances in Open Set Recognition: A Surveycited by 309
  7. 2018Meta-Learning: A Surveycited by 254
  8. 2014Towards Open World Recognitioncited by 226
  9. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  10. 2018Meta-Learning Probabilistic Inference For Predictioncited by 108
  11. 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
  12. 2018Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RLcited by 80
  13. 2015The Extreme Value Machinecited by 78
  14. 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 65
  15. 2019Continuous Meta-Learning without Taskscited by 50
  16. 2020Few-Shot Open-Set Recognition using Meta-Learningcited by 50
  17. 2018Meta-Learning Priors for Efficient Online Bayesian Regressioncited by 47
  18. 2019Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learningcited by 29
  19. 2020Wandering Within a World: Online Contextualized Few-Shot Learningcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 1; 2024: 4; 2025: 0; 2026: 1.

8 papers.

  1. 2024Variational Bayesian Last Layerscited by 67
  2. 2022A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biasescited by 30
  3. 2022Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learningcited by 23
  4. 2024Few-Shot Anomaly Detection via Category-Agnostic Registration Learningcited by 6
  5. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  6. 2024EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logitscited by 2
  7. 2023A Metalearned Neural Circuit for Nonparametric Bayesian Inferencecited by 1
  8. 2026UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Constructioncited by 0