mlsanityData to 7 Oct 2026

Adaptive Poincar'e Point to Set Distance for Few-Shot Classification

arXiv 2112.01719 ↗First posted 3 Dec 2021cs.CV cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Learning and generalizing from limited examples, i,e, few-shot learning, is of core importance to many real-world vision applications. A principal way of achieving few-shot learning is to realize an embedding where samples from different classes are distinctive. Recent studies suggest that embedding via hyperbolic geometry enjoys low distortion for hierarchical and structured data, making it suitable for few-shot learning. In this paper, we propose to learn a context-aware hyperbolic metric to characterize the distance between a point and a set associated with a learned set to set distance. To this end, we formulate the metric as a weighted sum on the tangent bundle of the hyperbolic space and develop a mechanism to obtain the weights adaptively and based on the constellation of the points. This not only makes the metric local but also dependent on the task in hand, meaning that the metric will adapt depending on the samples that it compares. We empirically show that such metric yields robustness in the presence of outliers and achieves a tangible improvement over baseline models. This includes the state-of-the-art results on five popular few-shot classification benchmarks, namely mini-ImageNet, tiered-ImageNet, Caltech-UCSD Birds-200-2011 (CUB), CIFAR-FS, and FC100.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 3 Dec 2021.

Builds on

39 of 55 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  8. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  9. 2019A Closer Look at Few-shot Classificationcited by 679
  10. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  11. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  12. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
27 more
  1. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  2. 2018Bilevel Programming for Hyperparameter Optimization and Meta-Learningcited by 403
  3. 2018Meta-learning with differentiable closed-form solverscited by 395
  4. 2018Hyperbolic Neural Networkscited by 393
  5. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  6. 2018How to train your MAMLcited by 306
  7. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  8. 2019Hyperbolic Image Embeddingscited by 219
  9. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  10. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  11. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  12. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  13. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  14. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  15. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  16. 2019Meta-Learning with Warped Gradient Descentcited by 98
  17. 2019When Does Self-supervision Improve Few-shot Learning?cited by 78
  18. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  19. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  20. 2019Transductive Episodic-Wise Adaptive Metric for Few-Shot Learningcited by 67
  21. 2019Few-Shot Learning with Embedded Class Models and Shot-Free Meta Trainingcited by 57
  22. 2020Instance Credibility Inference for Few-Shot Learningcited by 57
  23. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  24. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  25. 2021Reinforced Attention for Few-Shot Learning and Beyondcited by 18
  26. 2020Set Augmented Triplet Loss for Video Person Re-Identificationcited by 5
  27. 2019Learning to Generalize to Unseen Tasks with Bilevel Optimizationcited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 6; 2024: 1; 2025: 4.

15 papers.

Sort:

  1. 2023Hyperbolic Deep Learning in Computer Vision: A Surveycited by 72
  2. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  3. 2023Poincar'e ResNetcited by 24
  4. 2023Hyperbolic Audio-visual Zero-shot Learningcited by 19
  5. 2022Curved Geometric Networks for Visual Anomaly Recognitioncited by 15
  6. 2022RankDNN: Learning to Rank for Few-shot Learningcited by 7
  7. 2021Learning Instance and Task-Aware Dynamic Kernels for Few Shot Learningcited by 4
  8. 2023Hyperbolic Geometry in Computer Vision: A Surveycited by 4
  9. 2024When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weathercited by 4
  10. 2023Few-shot Classification via Ensemble Learning with Multi-Order Statisticscited by 3
  11. 2023Compositional Prototypical Networks for Few-Shot Classificationcited by 1
  12. 2025Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectorscited by 1
3 more
  1. 2025Rethinking the Sample Relations for Few-Shot Classificationcited by 0
  2. 2025State Space Models for Extractive Summarization in Low Resource Scenarioscited by 0
  3. 2025A Set-to-Set Distance Measure in Hyperbolic Spacecited by 0