mlsanityData to 14 Oct 2026

Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings

arXiv 2209.11481 ↗First posted 23 Sep 2022cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

We consider a novel formulation of the problem of Active Few-Shot Classification (AFSC) where the objective is to classify a small, initially unlabeled, dataset given a very restrained labeling budget. This problem can be seen as a rival paradigm to classical Transductive Few-Shot Classification (TFSC), as both these approaches are applicable in similar conditions. We first propose a methodology that combines statistical inference, and an original two-tier active learning strategy that fits well into this framework. We then adapt several standard vision benchmarks from the field of TFSC. Our experiments show the potential benefits of AFSC can be substantial, with gains in average weighted accuracy of up to 10% compared to state-of-the-art TFSC methods for the same labeling budget. We believe this new paradigm could lead to new developments and standards in data-scarce learning settings.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 44 references that are in the map. First posted on arXiv 23 Sep 2022.

Builds on

28 of 44 references.

References · 28

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  6. 2019Simplifying Graph Convolutional Networkscited by 1,477
  7. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  8. 2017Deep Bayesian Active Learning with Image Datacited by 819
  9. 2019A Closer Look at Few-shot Classificationcited by 684
  10. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  11. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  12. 2019A Baseline for Few-Shot Image Classificationcited by 298
16 more
  1. 2019Cross Attention Network for Few-shot Classificationcited by 219
  2. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
  3. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 166
  4. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  5. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  6. 2019Prototype Rectification for Few-Shot Learningcited by 97
  7. 2020Laplacian Regularized Few-Shot Learningcited by 92
  8. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  9. 2018Less is more: sampling chemical space with active learningcited by 82
  10. 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 74
  11. 2022GALAXY: Graph-based Active Learning at the Extremecited by 29
  12. 2021Self-Supervised Classification Networkcited by 28
  13. 2022Realistic Evaluation of Transductive Few-Shot Learningcited by 27
  14. 2022EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredientscited by 16
  15. 2022Active Few-Shot Learning with FASLcited by 11
  16. 2017Semi-Supervised and Active Few-Shot Learning with Prototypical Networkscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Assessing Low Back Movement with Motion Tape Sensor Data Through Deep Learningcited by 0