mlsanityData to 7 Oct 2026

Trainable Class Prototypes for Few-Shot Learning

arXiv 2106.10846 ↗First posted 21 Jun 2021cs.CV cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm. In this paper we propose the trainable prototypes for distance measure instead of the artificial ones within the meta-training and task-training framework. Also to avoid the disadvantages that the episodic meta-training brought, we adopt non-episodic meta-training based on self-supervised learning. Overall we solve the few-shot tasks in two phases: meta-training a transferable feature extractor via self-supervised learning and training the prototypes for metric classification. In addition, the simple attention mechanism is used in both meta-training and task-training. Our method achieves state-of-the-art performance in a variety of established few-shot tasks on the standard few-shot visual classification dataset, with about 20% increase compared to the available unsupervised few-shot learning methods.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 34 references that are in the map. First posted on arXiv 21 Jun 2021.

Builds on

31 of 34 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2017Neural Discrete Representation Learningcited by 4,650
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  10. 2017Non-local Neural Networkscited by 2,290
  11. 2016Matching Networks for One Shot Learningcited by 2,246
  12. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
19 more
  1. 2019Simplifying Graph Convolutional Networkscited by 1,470
  2. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  3. 2019Contrastive Multiview Codingcited by 1,297
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  5. 2016Colorful Image Colorizationcited by 1,113
  6. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  7. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  8. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  9. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  10. 2020Online Deep Clustering for Unsupervised Representation Learningcited by 99
  11. 2018Unsupervised Learning via Meta-Learningcited by 81
  12. 2018Unsupervised Meta-Learning For Few-Shot Image Classificationcited by 74
  13. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  14. 2019LGM-Net: Learning to Generate Matching Networks for Few-Shot Learningcited by 27
  15. 2019Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentationcited by 24
  16. 2019Unsupervised Few-shot Learning via Self-supervised Trainingcited by 7
  17. 2020Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classificationcited by 7
  18. 2020Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentationcited by 7
  19. 2020Few-Shot Image Classification via Contrastive Self-Supervised Learningcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024BECLR: Batch Enhanced Contrastive Few-Shot Learningcited by 6