mlsanityData to 14 Oct 2026

Learning to Compare: Relation Network for Few-Shot Learning

arXiv 1711.06025 ↗First posted 16 Nov 2017cs.CVcited by 1,143

Not on the map. Why?

Abstract (arXiv)

We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is designed to simulate the few-shot setting. Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network. Besides providing improved performance on few-shot learning, our framework is easily extended to zero-shot learning. Extensive experiments on five benchmarks demonstrate that our simple approach provides a unified and effective approach for both of these two tasks.

Key facts. Cited by 1,143 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 1; 2021: 335; 2022: 296; 2023: 228; 2024: 144; 2025: 87; 2026: 51.

1,143 papers.

Sort:

By area:

  1. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 431
  2. 2021Deep Long-Tailed Learning: A Surveycited by 417
  3. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 362
  4. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
  5. 2021SMIL: Multimodal Learning with Severely Missing Modalitycited by 245
  6. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  7. 2021Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentationcited by 203
  8. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  9. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  10. 2023Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learnerscited by 152
  11. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  12. 2022Registration based Few-Shot Anomaly Detectioncited by 133
38 more
  1. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 127
  2. 2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 126
  3. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  4. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 118
  5. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  6. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  7. 2023Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learningcited by 116
  8. 2022Hyperbolic Vision Transformers: Combining Improvements in Metric Learningcited by 111
  9. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  10. 2024Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observationcited by 104
  11. 2021On the Role of Neural Collapse in Transfer Learningcited by 100
  12. 2021Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learningcited by 96
  13. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  14. 2022"This is my unicorn, Fluffy": Personalizing frozen vision-language representationscited by 95
  15. 2024EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real Worldcited by 95
  16. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  17. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  18. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 88
  19. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  20. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  21. 2021Few-Shot Graph Learning for Molecular Property Predictioncited by 81
  22. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  23. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
  24. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  25. 2021Relational Embedding for Few-Shot Classificationcited by 74
  26. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  27. 2021Learning Normal Dynamics in Videos with Meta Prototype Networkcited by 71
  28. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  29. 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
  30. 2021Learn to Match: Automatic Matching Network Design for Visual Trackingcited by 67
  31. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  32. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  33. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  34. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  35. 2021Recurrent Mask Refinement for Few-Shot Medical Image Segmentationcited by 63
  36. 2021Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyondcited by 63
  37. 2021Learning a Universal Template for Few-shot Dataset Generalizationcited by 61
  38. 2021Few-Shot Lifelong Learningcited by 59

50 most cited of 1,143 All 1,143 (JSON)