mlsanityData to 7 Oct 2026

Boosting Few-Shot Learning With Adaptive Margin Loss

arXiv 2005.13826 ↗First posted 28 May 2020cs.CV cs.LG stat.MLcited by 83

Not on the map. Why?

Abstract (arXiv)

Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples. This paper proposes an adaptive margin principle to improve the generalization ability of metric-based meta-learning approaches for few-shot learning problems. Specifically, we first develop a class-relevant additive margin loss, where semantic similarity between each pair of classes is considered to separate samples in the feature embedding space from similar classes. Further, we incorporate the semantic context among all classes in a sampled training task and develop a task-relevant additive margin loss to better distinguish samples from different classes. Our adaptive margin method can be easily extended to a more realistic generalized FSL setting. Extensive experiments demonstrate that the proposed method can boost the performance of current metric-based meta-learning approaches, under both the standard FSL and generalized FSL settings.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 18; 2023: 18; 2024: 13; 2025: 5; 2026: 3.

83 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  3. 2021Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptionscited by 53
  4. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  5. 2022Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigationcited by 45
  6. 2021Orthogonal Projection Losscited by 44
  7. 2023Black Box Few-Shot Adaptation for Vision-Language modelscited by 39
  8. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
  9. 2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
  10. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 28
  11. 2021Binocular Mutual Learning for Improving Few-shot Classificationcited by 26
  12. 2021Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentationcited by 23
38 more
  1. 2021Prototype Guided Federated Learning of Visual Feature Representationscited by 22
  2. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  3. 2022Task Discrepancy Maximization for Fine-grained Few-Shot Classificationcited by 21
  4. 2023Learning to Learn from APIs: Black-Box Data-Free Meta-Learningcited by 18
  5. 2021Few-Shot Learning with a Strong Teachercited by 16
  6. 2021SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learningcited by 15
  7. 2021Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attentioncited by 15
  8. 2023Simple Semantic-Aided Few-Shot Learningcited by 15
  9. 2021Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learningcited by 12
  10. 2023FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learningcited by 12
  11. 2021Federated Few-Shot Learning with Adversarial Learningcited by 11
  12. 2021Boosting Few-Shot Classification with View-Learnable Contrastive Learningcited by 11
  13. 2021What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Datacited by 10
  14. 2023Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learningcited by 10
  15. 2024Boosting Few-Shot Learning via Attentive Feature Regularizationcited by 10
  16. 2022Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognitioncited by 9
  17. 2022Modelling Commonsense Properties using Pre-Trained Bi-Encoderscited by 9
  18. 2021Revisiting Local Descriptor for Improved Few-Shot Classificationcited by 8
  19. 2022Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Samplingcited by 8
  20. 2023Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Modelscited by 8
  21. 2024Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learningcited by 8
  22. 2021Prototype Completion for Few-Shot Learningcited by 7
  23. 2024Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo Simulationcited by 7
  24. 2024Making Large Vision Language Models to be Good Few-shot Learnerscited by 7
  25. 2025VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learningcited by 7
  26. 2021Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learningcited by 6
  27. 2023Advancing Incremental Few-shot Semantic Segmentation via Semantic-guided Relation Alignment and Adaptationcited by 6
  28. 2024Selective Annotation via Data Allocation: These Data Should Be Triaged to Experts for Annotation Rather Than the Modelcited by 6
  29. 2022Class Impression for Data-free Incremental Learningcited by 4
  30. 2022AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discriminationcited by 4
  31. 2023DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlationcited by 4
  32. 2023Task-Oriented Channel Attention for Fine-Grained Few-Shot Classificationcited by 4
  33. 2023Task-Distributionally Robust Data-Free Meta-Learningcited by 4
  34. 2024DiffCLIP: Few-shot Language-driven Multimodal Classifiercited by 4
  35. 2025Adaptive Margin Contrastive Learning for Ambiguity-aware 3D Semantic Segmentationcited by 4
  36. 2021Few-shot Image Classification with Multi-Facet Prototypescited by 3
  37. 2021Few-shot Partial Multi-view Learningcited by 3
  38. 2021Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detectioncited by 3

50 most cited of 83 All 83 (JSON)