mlsanityData to 14 Oct 2026

Instance-based Max-margin for Practical Few-shot Recognition

arXiv 2305.17368 ↗First posted 27 May 2023cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

In order to mimic the human few-shot learning (FSL) ability better and to make FSL closer to real-world applications, this paper proposes a practical FSL (pFSL) setting. pFSL is based on unsupervised pretrained models (analogous to human prior knowledge) and recognizes many novel classes simultaneously. Compared to traditional FSL, pFSL is simpler in its formulation, easier to evaluate, more challenging and more practical. To cope with the rarity of training examples, this paper proposes IbM2, an instance-based max-margin method not only for the new pFSL setting, but also works well in traditional FSL scenarios. Based on the Gaussian Annulus Theorem, IbM2 converts random noise applied to the instances into a mechanism to achieve maximum margin in the many-way pFSL (or traditional FSL) recognition task. Experiments with various self-supervised pretraining methods and diverse many- or few-way FSL tasks show that IbM2 almost always leads to improvements compared to its respective baseline methods, and in most cases the improvements are significant. With both the new pFSL setting and novel IbM2 method, this paper shows that practical few-shot learning is both viable and promising.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 40 of its 51 references that are in the map. First posted on arXiv 27 May 2023.

Builds on

40 of 51 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  8. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  10. 2016Wide Residual Networkscited by 3,070
  11. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  12. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
28 more
  1. 2016Matching Networks for One Shot Learningcited by 2,255
  2. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  3. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  4. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  5. 2019A Closer Look at Few-shot Classificationcited by 684
  6. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  7. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  8. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  9. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  10. 2018Meta-learning with differentiable closed-form solverscited by 397
  11. 2022Masked Siamese Networks for Label-Efficient Learningcited by 302
  12. 2019A Baseline for Few-Shot Image Classificationcited by 298
  13. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  14. 2018Probabilistic Model-Agnostic Meta-Learningcited by 256
  15. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  16. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  17. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  18. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  19. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  20. 2019When Does Self-supervision Improve Few-shot Learning?cited by 78
  21. 2021Distilling Virtual Examples for Long-tailed Recognitioncited by 72
  22. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  23. 2022Few-Shot Classification with Contrastive Learningcited by 31
  24. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  25. 2022Self-Supervision Can Be a Good Few-Shot Learnercited by 19
  26. 2022Worst Case Matters for Few-Shot Recognitioncited by 4
  27. 2022Exploring Effective Knowledge Transfer for Few-shot Object Detectioncited by 3
  28. 2022Better Generalized Few-Shot Learning Even Without Base Datacited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learningcited by 8
  2. 2024All You Need in Knowledge Distillation Is a Tailored Coordinate Systemcited by 6
  3. 2024Rectify the Regression Bias in Long-Tailed Object Detectioncited by 5
  4. 2025Contrastive Representation Distillation via Multi-Scale Feature Decouplingcited by 0
  5. 2025Color as the Impetus: Transforming Few-Shot Learnercited by 0
  6. 2026ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarioscited by 0