mlsanityData to 7 Oct 2026

Diversity with Cooperation: Ensemble Methods for Few-Shot Classification

arXiv 1903.11341 ↗First posted 27 Mar 2019cs.CV cs.AIcited by 70

Not on the map. Why?

Abstract (arXiv)

Few-shot classification consists of learning a predictive model that is able to effectively adapt to a new class, given only a few annotated samples. To solve this challenging problem, meta-learning has become a popular paradigm that advocates the ability to "learn to adapt". Recent works have shown, however, that simple learning strategies without meta-learning could be competitive. In this paper, we go a step further and show that by addressing the fundamental high-variance issue of few-shot learning classifiers, it is possible to significantly outperform current meta-learning techniques. Our approach consists of designing an ensemble of deep networks to leverage the variance of the classifiers, and introducing new strategies to encourage the networks to cooperate, while encouraging prediction diversity. Evaluation is conducted on the mini-ImageNet and CUB datasets, where we show that even a single network obtained by distillation yields state-of-the-art results.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 22; 2023: 10; 2024: 7; 2025: 2; 2026: 3.

70 papers.

Sort:

By area:

  1. 2023Deep Model Fusion: A Surveycited by 89
  2. 2022Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 63
  3. 2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
  4. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  5. 2021DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimationcited by 48
  6. 2022Preserving Privacy in Federated Learning with Ensemble Cross-Domain Knowledge Distillationcited by 45
  7. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  8. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  9. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
  10. 2021Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifiercited by 32
  11. 2022Memorizing Complementation Network for Few-Shot Class-Incremental Learningcited by 30
  12. 2021Class-Balanced Distillation for Long-Tailed Visual Recognitioncited by 27
38 more
  1. 2023MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognitioncited by 26
  2. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  3. 2021A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applicationscited by 24
  4. 2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
  5. 2021Selective Ensembles for Consistent Predictionscited by 23
  6. 2022Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generationcited by 20
  7. 2021Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learningcited by 19
  8. 2022Self-Supervision Can Be a Good Few-Shot Learnercited by 19
  9. 2021Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIscited by 16
  10. 2021Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentationcited by 15
  11. 2021On the Importance of Distractors for Few-Shot Classificationcited by 14
  12. 2023NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 14
  13. 2022Diagnosing Ensemble Few-Shot Classifierscited by 13
  14. 2022Feature Space Particle Inference for Neural Network Ensemblescited by 9
  15. 2022Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuningcited by 9
  16. 2023GeNIe: Generative Hard Negative Images Through Diffusioncited by 8
  17. 2021On the Importance of Firth Bias Reduction in Few-Shot Classificationcited by 7
  18. 2021MHFC: Multi-Head Feature Collaboration for Few-Shot Learningcited by 6
  19. 2022Lifelong Ensemble Learning based on Multiple Representations for Few-Shot Object Recognitioncited by 6
  20. 2022SAGE: Saliency-Guided Mixup with Optimal Rearrangementscited by 6
  21. 2021Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learningcited by 5
  22. 2021MDFM: Multi-Decision Fusing Model for Few-Shot Learningcited by 5
  23. 2022GCT: Graph Co-Training for Semi-Supervised Few-Shot Learningcited by 5
  24. 2021Local Propagation for Few-Shot Learningcited by 4
  25. 2021Ensemble Making Few-Shot Learning Strongercited by 4
  26. 2021Multi-headed Neural Ensemble Searchcited by 4
  27. 2022Worst Case Matters for Few-Shot Recognitioncited by 4
  28. 2022Revisiting Few-Shot Learning from a Causal Perspectivecited by 4
  29. 2022PatchMix Augmentation to Identify Causal Features in Few-shot Learningcited by 4
  30. 2023Local Learning with Neuron Groupscited by 4
  31. 2022Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approachcited by 3
  32. 2022Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learningcited by 3
  33. 2023Few-shot Classification via Ensemble Learning with Multi-Order Statisticscited by 3
  34. 2023Towards Open Federated Learning Platforms: Survey and Vision from Technical and Legal Perspectivescited by 3
  35. 2024WiFlexFormer: Efficient WiFi-Based Person-Centric Sensingcited by 3
  36. 2022Meta-free few-shot learning via representation learning with weight averagingcited by 2
  37. 2025Learning Task-Agnostic Representations through Multi-Teacher Distillationcited by 2
  38. 2026A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helpscited by 2

50 most cited of 70 All 70 (JSON)