mlsanityData to 7 Oct 2026

Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments

arXiv 2105.08149 ↗First posted 17 May 2021cs.CV cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

Few-shot image classification is a challenging problem that aims to achieve the human level of recognition based only on a small number of training images. One main solution to few-shot image classification is deep metric learning. These methods, by classifying unseen samples according to their distances to few seen samples in an embedding space learned by powerful deep neural networks, can avoid overfitting to few training images in few-shot image classification and have achieved the state-of-the-art performance. In this paper, we provide an up-to-date review of deep metric learning methods for few-shot image classification from 2018 to 2022 and categorize them into three groups according to three stages of metric learning, namely learning feature embeddings, learning class representations, and learning distance measures. With this taxonomy, we identify the novelties of different methods and problems they face. We conclude this review with a discussion on current challenges and future trends in few-shot image classification.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 69 of its 127 references that are in the map. First posted on arXiv 17 May 2021.

Builds on

69 of 127 references.

References · 69

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2014Going Deeper with Convolutionscited by 4,231
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  9. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  10. 2019A Closer Look at Few-shot Classificationcited by 679
  11. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
  12. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
38 more
  1. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  2. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  3. 2018Meta-learning with differentiable closed-form solverscited by 395
  4. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  5. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  6. 2015Recent Advances in Convolutional Neural Networkscited by 360
  7. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  8. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  9. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  10. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  11. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  12. 2017Data Augmentation Generative Adversarial Networkscited by 278
  13. 2016Data Programming: Creating Large Training Sets, Quicklycited by 246
  14. 2020What Should Not Be Contrastive in Contrastive Learningcited by 224
  15. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  16. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  17. 2018Low-Shot Learning from Imaginary Datacited by 181
  18. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  19. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  20. 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
  21. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  22. 2015Deep Convolutional Inverse Graphics Networkcited by 121
  23. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  24. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  25. 2019Improved Few-Shot Visual Classificationcited by 114
  26. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  27. 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
  28. 2017Learning to Compose Domain-Specific Transformations for Data Augmentationcited by 91
  29. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 90
  30. 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
  31. 2020Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognitioncited by 69
  32. 2019Transductive Episodic-Wise Adaptive Metric for Few-Shot Learningcited by 67
  33. 2019Few-Shot Learning with Embedded Class Models and Shot-Free Meta Trainingcited by 57
  34. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  35. 2019Few-Shot Learning via Saliency-guided Hallucination of Samplescited by 49
  36. 2020Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Ratescited by 49
  37. 2019Few-Shot Learning with Global Class Representationscited by 44
  38. 2020Momentum Contrastive Learning for Few-Shot COVID-19 Diagnosis from Chest CT Imagescited by 43

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 9; 2025: 2; 2026: 4.

23 papers.

Sort:

By area:

  1. 2024SDR-Former: A Siamese Dual-Resolution Transformer for Liver Lesion Classification Using 3D Multi-Phase Imagingcited by 17
  2. 2022HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworkscited by 16
  3. 2022Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classificationcited by 12
  4. 2023HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognitioncited by 12
  5. 2023Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationcited by 11
  6. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  7. 2024Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learningcited by 7
  8. 2022Enhancing Few-shot Image Classification with Cosine Transformercited by 4
  9. 2023Masked Momentum Contrastive Learning for Zero-shot Semantic Understandingcited by 4
  10. 2024Latent Representation Matters: Human-like Sketches in One-shot Drawing Taskscited by 3
  11. 2022Probabilistic Deep Metric Learning for Hyperspectral Image Classificationcited by 2
  12. 2024Knowledge-enhanced Relation Graph and Task Sampling for Few-shot Molecular Property Predictioncited by 2
11 more
  1. 2023Weighted Unsupervised Domain Adaptation Considering Geometry Features and Engineering Performance of 3D Design Datacited by 1
  2. 2024Meta-Transfer Derm-Diagnosis: Exploring Few-Shot Learning and Transfer Learning for Skin Disease Classification in Long-Tail Distributioncited by 1
  3. 2024UNEM: UNrolled Generalized EM for Transductive Few-Shot Learningcited by 1
  4. 2025A Survey on Small Sample Imbalance Problem: Metrics, Feature Analysis, and Solutionscited by 1
  5. 2024Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metriccited by 0
  6. 2024Hyperspectral Imaging-Based Grain Quality Assessment With Limited Labelled Datacited by 0
  7. 2025Large Language Model Aided Birt-Hogg-Dube Syndrome Diagnosis with Multimodal Retrieval-Augmented Generationcited by 0
  8. 2026PEARL: Prototype-Enhanced Alignment for Label-Efficient Representation Learning with Deployment-Driven Insights from Digital Governance Communication Systemscited by 0
  9. 2026A Dual-Stream Physics-Augmented Unsupervised Architecture for Runtime Embedded Vehicle Health Monitoringcited by 0
  10. 2026OSCS-SupCon: Orthogonal Sigmoid-based Common and Style Supervised Contrastive Learning for Robust Feature Disentanglementcited by 0
  11. 2026Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learningcited by 0