mlsanityData to 7 Oct 2026

Relational Embedding for Few-Shot Classification

arXiv 2108.09666 ↗First posted 22 Aug 2021cs.CVcited by 74

Not on the map. Why?

Abstract (arXiv)

We propose to address the problem of few-shot classification by meta-learning "what to observe" and "where to attend" in a relational perspective. Our method leverages relational patterns within and between images via self-correlational representation (SCR) and cross-correlational attention (CCA). Within each image, the SCR module transforms a base feature map into a self-correlation tensor and learns to extract structural patterns from the tensor. Between the images, the CCA module computes cross-correlation between two image representations and learns to produce co-attention between them. Our Relational Embedding Network (RENet) combines the two relational modules to learn relational embedding in an end-to-end manner. In experimental evaluation, it achieves consistent improvements over state-of-the-art methods on four widely used few-shot classification benchmarks of miniImageNet, tieredImageNet, CUB-200-2011, and CIFAR-FS.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). Builds on 67 of its 92 references that are in the map. First posted on arXiv 22 Aug 2021.

Builds on

67 of 92 references.

References · 67

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2014Going Deeper with Convolutionscited by 4,231
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2016Matching Networks for One Shot Learningcited by 2,246
  11. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  12. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
38 more
  1. 2014How transferable are features in deep neural networks?cited by 1,216
  2. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  3. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  4. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  5. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  6. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  7. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  8. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  9. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  10. 2019Video Object Segmentation using Space-Time Memory Networkscited by 436
  11. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  12. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  13. 2018Meta-learning with differentiable closed-form solverscited by 395
  14. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  15. 2020Exploring Self-attention for Image Recognitioncited by 313
  16. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  17. 2019A Baseline for Few-Shot Image Classificationcited by 298
  18. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  19. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  20. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  21. 2019Cross Attention Network for Few-shot Classificationcited by 218
  22. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  23. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
  24. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  25. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  26. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  27. 2018Neighbourhood Consensus Networkscited by 173
  28. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
  29. 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
  30. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  31. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  32. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  33. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  34. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  35. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  36. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  37. 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
  38. 2018VideoMatch: Matching based Video Object Segmentationcited by 90

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 28; 2023: 16; 2024: 16; 2025: 9; 2026: 2.

74 papers.

Sort:

By area:

  1. 2024Local All-Pair Correspondence for Point Trackingcited by 77
  2. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  3. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  4. 2022Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?cited by 31
  5. 2022Few-Shot Classification with Contrastive Learningcited by 31
  6. 2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Miningcited by 30
  7. 2022Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignmentcited by 29
  8. 2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
  9. 2022Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learningcited by 27
  10. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  11. 2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
  12. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
38 more
  1. 2023Supervised Masked Knowledge Distillation for Few-Shot Transformerscited by 23
  2. 2022Self-Promoted Supervision for Few-Shot Transformercited by 22
  3. 2022Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignmentscited by 22
  4. 2021LibFewShot: A Comprehensive Library for Few-shot Learningcited by 21
  5. 2022Task Discrepancy Maximization for Fine-grained Few-Shot Classificationcited by 21
  6. 2023Does Few-shot Learning Suffer from Backdoor Attacks?cited by 19
  7. 2024Learning Correlation Structures for Vision Transformerscited by 15
  8. 2021Sparse Spatial Transformers for Few-Shot Learningcited by 14
  9. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  10. 2022Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregationcited by 14
  11. 2022Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classificationcited by 10
  12. 2022An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learningcited by 10
  13. 2023Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancementcited by 10
  14. 2024Boosting Few-Shot Learning via Attentive Feature Regularizationcited by 10
  15. 2022CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classificationcited by 9
  16. 2022Few-shot Metric Learning: Online Adaptation of Embedding for Retrievalcited by 8
  17. 2022The Self-Optimal-Transport Feature Transformcited by 7
  18. 2022RankDNN: Learning to Rank for Few-shot Learningcited by 7
  19. 2023ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learningcited by 6
  20. 2023Efficient Semantic Matching with Hypercolumn Correlationcited by 6
  21. 2024Benchmarking Spurious Bias in Few-Shot Image Classifierscited by 6
  22. 2024MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlationcited by 5
  23. 2024Learning to Obstruct Few-Shot Image Classification over Restricted Classescited by 5
  24. 2022Interpretable Concept-based Prototypical Networks for Few-Shot Learningcited by 4
  25. 2022Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulationcited by 4
  26. 2022Kernel Relative-prototype Spectral Filtering for Few-shot Learningcited by 4
  27. 2022Enhancing Few-shot Image Classification with Cosine Transformercited by 4
  28. 2023Task-Oriented Channel Attention for Fine-Grained Few-Shot Classificationcited by 4
  29. 2023Domain Adaptive Few-Shot Open-Set Learningcited by 4
  30. 2024Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformerscited by 4
  31. 2023Few-shot Classification via Ensemble Learning with Multi-Order Statisticscited by 3
  32. 2023Disentangled Representation Learning with Transmitted Information Bottleneckcited by 3
  33. 2023FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?cited by 2
  34. 2023Tabular Few-Shot Generalization Across Heterogeneous Feature Spacescited by 2
  35. 2023Few-Shot Classification & Segmentation Using Large Language Models Agentcited by 2
  36. 2024The Balanced-Pairwise-Affinities Feature Transformcited by 2
  37. 2022Learning Compositional Representations for Effective Low-Shot Generalizationcited by 1
  38. 2022BaseTransformers: Attention over base data-points for One Shot Learningcited by 1

50 most cited of 74 All 74 (JSON)