mlsanityData to 7 Oct 2026

A Closer Look at Few-shot Classification Again

arXiv 2301.12246 ↗First posted 28 Jan 2023cs.LG cs.CVcited by 46

Not on the map. Why?

Abstract (arXiv)

Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper, we empirically prove that the training algorithm and the adaptation algorithm can be completely disentangled, which allows algorithm analysis and design to be done individually for each phase. Our meta-analysis for each phase reveals several interesting insights that may help better understand key aspects of few-shot classification and connections with other fields such as visual representation learning and transfer learning. We hope the insights and research challenges revealed in this paper can inspire future work in related directions. Code and pre-trained models (in PyTorch) are available at https://github.com/Frankluox/CloserLookAgainFewShot.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Builds on 75 of its 98 references that are in the map. First posted on arXiv 28 Jan 2023.

Builds on

75 of 98 references.

References · 75

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  10. 2016Densely Connected Convolutional Networkscited by 6,691
  11. 2020Scaling Laws for Neural Language Modelscited by 6,411
  12. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
38 more
  1. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  2. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2022A ConvNet for the 2020scited by 3,545
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  7. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  8. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  9. 2016Matching Networks for One Shot Learningcited by 2,246
  10. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  11. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  12. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  13. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  14. 2021Scaling Vision Transformerscited by 993
  15. 2020Designing Network Design Spacescited by 954
  16. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  17. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 891
  18. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  19. 2019A Closer Look at Few-shot Classificationcited by 679
  20. 2018Do Better ImageNet Models Transfer Better?cited by 560
  21. 2017Deep Learning Scaling is Predictable, Empiricallycited by 556
  22. 2019Meta-Learning with Implicit Gradientscited by 523
  23. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  24. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  25. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  26. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
  27. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  28. 2018Conditional Neural Processescited by 421
  29. 2019A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmarkcited by 419
  30. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  31. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  32. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  33. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  34. 2019A Baseline for Few-Shot Image Classificationcited by 298
  35. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  36. 2017Meta Networkscited by 268
  37. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  38. 2020CrossTransformers: spatially-aware few-shot transfercited by 174

50 most cited of 75 All 75 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 19; 2025: 12; 2026: 9.

46 papers.

Sort:

By area:

  1. 2023DePT: Decoupled Prompt Tuningcited by 58
  2. 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
  3. 2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentationcited by 22
  4. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  5. 2025Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detectioncited by 14
  6. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  7. 2024A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Modelscited by 13
  8. 2024Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Datacited by 12
  9. 2023From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learningcited by 9
  10. 2024Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacousticscited by 7
  11. 2025A Closer Look at Conditional Prompt Tuning for Vision-Language Modelscited by 7
  12. 2023ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrievalcited by 6
34 more
  1. 2024MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototypingcited by 5
  2. 2026Billion-Scale Graph Foundation Modelscited by 5
  3. 2024Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognitioncited by 4
  4. 2025Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropycited by 4
  5. 2023Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learningcited by 3
  6. 2024Context-Aware Multimodal Pretrainingcited by 3
  7. 2024Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Modelscited by 2
  8. 2024Towards Generative Class Prompt Learning for Fine-grained Visual Recognitioncited by 2
  9. 2024Cross-Modal Few-Shot Learning: a Generative Transfer Learning Frameworkcited by 2
  10. 2025Few-Shot Learning in Video and 3D Object Detection: A Surveycited by 2
  11. 2026Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypescited by 2
  12. 2024UNEM: UNrolled Generalized EM for Transductive Few-Shot Learningcited by 1
  13. 2025FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learningcited by 1
  14. 2025CCoMAML: Efficient Cattle Identification Using Cooperative Model-Agnostic Meta-Learningcited by 1
  15. 2026Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocolscited by 1
  16. 2026Rethinking the Good Enough Embedding for Easy Few-Shot Learningcited by 1
  17. 2023TransMed: Large Language Models Enhance Vision Transformer for Biomedical Image Classificationcited by 0
  18. 2024Few and Fewer: Learning Better from Few Examples Using Fewer Base Classescited by 0
  19. 2024A Strong Baseline for Molecular Few-Shot Learningcited by 0
  20. 2024Flatness Improves Backbone Generalisation in Few-shot Classificationcited by 0
  21. 2024Enhancing Document-level Argument Extraction with Definition-augmented Heuristic-driven Prompting for LLMscited by 0
  22. 2024Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learningcited by 0
  23. 2024Unsupervised Meta-Learning via Dynamic Head and Heterogeneous Task Construction for Few-Shot Classificationcited by 0
  24. 2024Hyperspectral Imaging-Based Grain Quality Assessment With Limited Labelled Datacited by 0
  25. 2025Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classificationcited by 0
  26. 2025MetaDSE: A Few-shot Meta-learning Framework for Cross-workload CPU Design Space Explorationcited by 0
  27. 2025Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learningcited by 0
  28. 2025Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domainscited by 0
  29. 2025MetaChest: Generalized few-shot learning of pathologies from chest X-rayscited by 0
  30. 2026PMCE: Probabilistic Multi-Granularity Semantics with Caption-Guided Enhancement for Few-Shot Learningcited by 0
  31. 2026Universal Algorithm-Implicit Learningcited by 0
  32. 2026Torus embeddingscited by 0
  33. 2026Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recyclingcited by 0
  34. 2026Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptionscited by 0