mlsanityData to 7 Oct 2026

A Baseline for Few-Shot Image Classification

arXiv 1909.02729 ↗First posted 6 Sep 2019cs.LG cs.CV stat.MLcited by 298

Not on the map. Why?

Abstract (arXiv)

Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters. The simplicity of this approach enables us to demonstrate the first few-shot learning results on the ImageNet-21k dataset. We find that using a large number of meta-training classes results in high few-shot accuracies even for a large number of few-shot classes. We do not advocate our approach as the solution for few-shot learning, but simply use the results to highlight limitations of current benchmarks and few-shot protocols. We perform extensive studies on benchmark datasets to propose a metric that quantifies the "hardness" of a few-shot episode. This metric can be used to report the performance of few-shot algorithms in a more systematic way.

Key facts. Cited by 298 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 85; 2022: 78; 2023: 68; 2024: 35; 2025: 24; 2026: 8.

298 papers.

Sort:

By area:

  1. 2021Scaling Vision with Sparse Mixture of Expertscited by 740
  2. 2021ImageNet-21K Pretraining for the Massescited by 607
  3. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 429
  4. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
  5. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 180
  6. 2023StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learnerscited by 177
  7. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  8. 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoningcited by 160
  9. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
  10. 2021On the Role of Neural Collapse in Transfer Learningcited by 100
  11. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  12. 2023Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Modelscited by 91
38 more
  1. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  2. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  3. 2021Cross-domain Few-shot Learning with Task-specific Adapterscited by 79
  4. 2021Relational Embedding for Few-Shot Classificationcited by 74
  5. 2021FLEX: Unifying Evaluation for Few-Shot NLPcited by 67
  6. 2022Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weightscited by 63
  7. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  8. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  9. 2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
  10. 2023A Closer Look at Few-shot Classification Againcited by 46
  11. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  12. 2021Improved Regularization and Robustness for Fine-tuning in Neural Networkscited by 45
  13. 2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
  14. 2021Few-Shot Object Detection via Association and DIscriminationcited by 39
  15. 2023MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classificationcited by 38
  16. 2022Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficultycited by 37
  17. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
  18. 2024Boosting Vision-Language Models with Transductioncited by 36
  19. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  20. 2021Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgettingcited by 33
  21. 2021Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifiercited by 32
  22. 2023Leveraging sparse and shared feature activations for disentangled representation learningcited by 32
  23. 2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
  24. 2022Realistic Evaluation of Transductive Few-Shot Learningcited by 26
  25. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  26. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  27. 2022Transductive Linear Probing: A Novel Framework for Few-Shot Node Classificationcited by 24
  28. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
  29. 2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
  30. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  31. 2022A Strong Baseline for Generalized Few-Shot Semantic Segmentationcited by 22
  32. 2021LibFewShot: A Comprehensive Library for Few-shot Learningcited by 21
  33. 2023Learning Expressive Prompting With Residuals for Vision Transformerscited by 21
  34. 2022FHIST: A Benchmark for Few-shot Classification of Histological Imagescited by 20
  35. 2022Channel Importance Matters in Few-Shot Image Classificationcited by 20
  36. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  37. 2023The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifoldcited by 20
  38. 2023Context-Aware Meta-Learningcited by 20

50 most cited of 298 All 298 (JSON)