mlsanityData to 7 Oct 2026

Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification

arXiv 2208.12398 ↗First posted 26 Aug 2022cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Few-shot classification which aims to recognize unseen classes using very limited samples has attracted more and more attention. Usually, it is formulated as a metric learning problem. The core issue of few-shot classification is how to learn (1) consistent representations for images in both support and query sets and (2) effective metric learning for images between support and query sets. In this paper, we show that the two challenges can be well modeled simultaneously via a unified Query-Support TransFormer (QSFormer) model. To be specific,the proposed QSFormer involves global query-support sample Transformer (sampleFormer) branch and local patch Transformer (patchFormer) learning branch. sampleFormer aims to capture the dependence of samples in support and query sets for image representation. It adopts the Encoder, Decoder and Cross-Attention to respectively model the Support, Query (image) representation and Metric learning for few-shot classification task. Also, as a complementary to global learning branch, we adopt a local patch Transformer to extract structural representation for each image sample by capturing the long-range dependence of local image patches. In addition, a novel Cross-scale Interactive Feature Extractor (CIFE) is proposed to extract and fuse multi-scale CNN features as an effective backbone module for the proposed few-shot learning method. All modules are integrated into a unified framework and trained in an end-to-end manner. Extensive experiments on four popular datasets demonstrate the effectiveness and superiority of the proposed QSFormer.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 59 of its 89 references that are in the map. First posted on arXiv 26 Aug 2022.

Builds on

59 of 89 references.

References · 59

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2019A Closer Look at Few-shot Classificationcited by 679
  11. 2019Meta-Learning with Implicit Gradientscited by 523
  12. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
38 more
  1. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  2. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  3. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  4. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  5. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  6. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  7. 2021Medical Transformer: Gated Axial-Attention for Medical Image Segmentationcited by 319
  8. 2018How to train your MAMLcited by 306
  9. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  10. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  11. 2021Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Trackingcited by 220
  12. 2019Cross Attention Network for Few-shot Classificationcited by 218
  13. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  14. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  15. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  16. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  17. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  18. 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
  19. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  20. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  21. 2020General Multi-label Image Classification with Transformerscited by 126
  22. 2021Query2Label: A Simple Transformer Way to Multi-Label Classificationcited by 126
  23. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  24. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  25. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  26. 2019Meta-Learning with Warped Gradient Descentcited by 98
  27. 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
  28. 2021U-Net Transformer: Self and Cross Attention for Medical Image Segmentationcited by 81
  29. 2021M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformerscited by 74
  30. 2015Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameterscited by 71
  31. 2019Meta-Curvaturecited by 70
  32. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  33. 2020A Universal Representation Transformer Layer for Few-Shot Image Classificationcited by 65
  34. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  35. 2019Few-Shot Learning with Embedded Class Models and Shot-Free Meta Trainingcited by 57
  36. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  37. 2022HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learningcited by 55
  38. 2021RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representationcited by 52

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 4; 2026: 1.

16 papers.

Sort:

  1. 2024Transformer for Object Re-Identification: A Surveycited by 21
  2. 2024EDTformer: An Efficient Decoder Transformer for Visual Place Recognitioncited by 10
  3. 2023Mitigating the Effect of Incidental Correlations on Part-based Learningcited by 6
  4. 2024Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanismscited by 4
  5. 2024TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognitioncited by 3
  6. 2023Hint-Aug: Drawing Hints from Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuningcited by 2
  7. 2023LPN: Language-guided Prototypical Network for few-shot classificationcited by 1
  8. 2024Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognitioncited by 1
  9. 2024Intra-task Mutual Attention based Vision Transformer for Few-Shot Learningcited by 1
  10. 2024Class-relevant Patch Embedding Selection for Few-Shot Image Classificationcited by 1
  11. 2025Meta-Statistical Learning: Supervised Learning of Statistical Estimatorscited by 1
  12. 2024Siamese Transformer Networks for Few-shot Image Classificationcited by 0
4 more
  1. 2025Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classificationcited by 0
  2. 2025BATR-FST: Bi-Level Adaptive Token Refinement for Few-Shot Transformerscited by 0
  3. 2025A2M2-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognitioncited by 0
  4. 2026PMCE: Probabilistic Multi-Granularity Semantics with Caption-Guided Enhancement for Few-Shot Learningcited by 0