mlsanityData to 7 Oct 2026

Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier

arXiv 2101.00562 ↗First posted 3 Jan 2021cs.CV cs.AI cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality, pre-trained feature extractors for few-shot image classification. We show experimentally that a library of pre-trained feature extractors combined with a simple feed-forward network learned with an L2-regularizer can be an excellent option for solving cross-domain few-shot image classification. Our experimental results suggest that this simpler sample-efficient approach far outperforms several well-established meta-learning algorithms on a variety of few-shot tasks.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 3 Jan 2021.

Builds on

25 of 40 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2013Describing Textures in the Wildcited by 2,110
  8. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  11. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  12. 2019A Closer Look at Few-shot Classificationcited by 679
13 more
  1. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  2. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  3. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  4. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  5. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  6. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  7. 2019A Baseline for Few-Shot Image Classificationcited by 298
  8. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  9. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  10. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  11. 2018Low-Shot Learning from Imaginary Datacited by 181
  12. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  13. 2019Diversity with Cooperation: Ensemble Methods for Few-Shot Classificationcited by 70

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 11; 2023: 5; 2024: 5; 2025: 4; 2026: 2.

32 papers.

Sort:

By area:

  1. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 310
  2. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  3. 2022Memorizing Complementation Network for Few-Shot Class-Incremental Learningcited by 30
  4. 2022Few-shot Relational Reasoning via Connection Subgraph Pretrainingcited by 18
  5. 2022Learning useful representations for shifting tasks and distributionscited by 14
  6. 2021On the Convergence of Shallow Neural Network Training with Randomly Masked Neuronscited by 11
  7. 2022The Art of Prompting: Event Detection based on Type Specific Promptscited by 9
  8. 2023SARF: Aliasing Relation Assisted Self-Supervised Learning for Few-shot Relation Reasoningcited by 9
  9. 2022Few-shot Metric Learning: Online Adaptation of Embedding for Retrievalcited by 8
  10. 2022Lifelong Ensemble Learning based on Multiple Representations for Few-Shot Object Recognitioncited by 6
  11. 2022Enhancing Few-shot Image Classification with Cosine Transformercited by 4
  12. 2023Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones Are Difficult to Beatcited by 4
20 more
  1. 2024Enhanced Few-Shot Class-Incremental Learning via Ensemble Modelscited by 4
  2. 2024Targeted Augmentation for Low-Resource Event Extractioncited by 4
  3. 2025Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representationscited by 4
  4. 2023Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learningcited by 3
  5. 2024Fine-tuning with Very Large Dropoutcited by 3
  6. 2021Attentional Meta-learners for Few-shot Polythetic Classificationcited by 2
  7. 2023Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learningcited by 2
  8. 2025Fantastic Features and Where to Find Them: A Probing Method to combine Features from Multiple Foundation Modelscited by 2
  9. 2022Convolutional Ensembling based Few-Shot Defect Detection Techniquecited by 1
  10. 2023Advancing Image Retrieval with Few-Shot Learning and Relevance Feedbackcited by 1
  11. 2024Music auto-tagging in the long tail: A few-shot approachcited by 1
  12. 2024Low-Data Classification of Historical Music Manuscripts: A Few-Shot Learning Approachcited by 1
  13. 2021Few-Shot Learning for Image Classification of Common Floracited by 0
  14. 2021One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representationscited by 0
  15. 2021Improving traffic sign recognition by active searchcited by 0
  16. 2022Feature Transformation for Cross-domain Few-shot Remote Sensing Scene Classificationcited by 0
  17. 2025ELMF4EggQ: Ensemble Learning with Multimodal Feature Fusion for Non-Destructive Egg Quality Assessmentcited by 0
  18. 2025A Domain-Adapted Lightweight Ensemble for Resource-Efficient Few-Shot Plant Disease Classificationcited by 0
  19. 2026ChimeraLoRA: Multi-Head LoRA-Guided Synthetic Datasetscited by 0
  20. 2026Dual Contrastive Network for Few-Shot Remote Sensing Image Scene Classificationcited by 0