mlsanityData to 7 Oct 2026

Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training

arXiv 1905.04398 ↗First posted 10 May 2019cs.LG cs.CV stat.MLcited by 57

Not on the map. Why?

Abstract (arXiv)

We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of ways and any number of shots (shot-free). Rather than fixing the class prototypes to be the Euclidean average of sample embeddings, we allow them to live in a higher-dimensional space (embedded class models) and learn the prototypes along with the model parameters. The class representation function is defined implicitly, which allows us to deal with a variable number of shots per each class with a simple constant-size architecture. The class embedding encompasses metric learning, that facilitates adding new classes without crowding the class representation space. Despite being general and not tuned to the benchmark, our approach achieves state-of-the-art performance on the standard few-shot benchmark datasets.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 17; 2023: 5; 2024: 4; 2025: 0; 2026: 1.

57 papers.

Sort:

By area:

  1. 2021On the Role of Neural Collapse in Transfer Learningcited by 100
  2. 2021Relational Embedding for Few-Shot Classificationcited by 74
  3. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  4. 2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
  5. 2021Orthogonal Projection Losscited by 44
  6. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
  7. 2022Few-Shot Classification with Contrastive Learningcited by 31
  8. 2023MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognitioncited by 26
  9. 2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
  10. 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
  11. 2021Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learningcited by 22
  12. 2021Few-Shot Learning with a Strong Teachercited by 16
38 more
  1. 2022Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classificationcited by 16
  2. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  3. 2021SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learningcited by 15
  4. 2021Adaptive Poincar'e Point to Set Distance for Few-Shot Classificationcited by 15
  5. 2022Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregationcited by 14
  6. 2022Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transportcited by 14
  7. 2021The Role of Global Labels in Few-Shot Classification and How to Infer Themcited by 12
  8. 2021ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learningcited by 11
  9. 2021Label Hallucination for Few-Shot Classificationcited by 11
  10. 2022Cap2Aug: Caption guided Image to Image data Augmentationcited by 10
  11. 2021DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Networkcited by 9
  12. 2022Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Networkcited by 9
  13. 2023Federated Few-shot Learningcited by 9
  14. 2021Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awarenesscited by 8
  15. 2021Task Affinity with Maximum Bipartite Matching in Few-Shot Learningcited by 8
  16. 2022Generalization Bounds for Few-Shot Transfer Learning with Pretrained Classifierscited by 7
  17. 2023What Makes for Effective Few-shot Point Cloud Classification?cited by 7
  18. 2021Supervised Momentum Contrastive Learning for Few-Shot Classificationcited by 6
  19. 2021Uniform Sampling over Episode Difficultycited by 6
  20. 2022Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptilecited by 6
  21. 2021CORL: Compositional Representation Learning for Few-Shot Classificationcited by 4
  22. 2021Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learningcited by 4
  23. 2021Unsupervised Representation Learning Meets Pseudo-Label Supervised Self-Distillation: A New Approach to Rare Disease Classificationcited by 4
  24. 2022Schedule-Robust Online Continual Learningcited by 4
  25. 2023LSFSL: Leveraging Shape Information in Few-shot Learningcited by 4
  26. 2021Towards Enabling Meta-Learning from Target Modelscited by 3
  27. 2022A Simple Approach to Adversarial Robustness in Few-shot Image Classificationcited by 3
  28. 2022Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learningcited by 3
  29. 2022Meta-free few-shot learning via representation learning with weight averagingcited by 2
  30. 2022Unsupervised Few-shot Learning via Deep Laplacian Eigenmapscited by 2
  31. 2022Few-shot Classification with Hypersphere Modeling of Prototypescited by 2
  32. 2022Robust Meta-Representation Learning via Global Label Inference and Classificationcited by 2
  33. 2021Learning Class-level Prototypes for Few-shot Learningcited by 1
  34. 2021Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learningcited by 1
  35. 2022LAVA: Label-efficient Visual Learning and Adaptationcited by 1
  36. 2024Boosting Meta-Training with Base Class Information for Few-Shot Learningcited by 1
  37. 2024Multi-Level Correlation Network For Few-Shot Image Classificationcited by 1
  38. 2021Few-shot Learning with Global Relatedness Decoupled-Distillationcited by 0

50 most cited of 57 All 57 (JSON)