mlsanityData to 7 Oct 2026

Clustered-patch Element Connection for Few-shot Learning

arXiv 2304.10093 ↗First posted 20 Apr 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Weak feature representation problem has influenced the performance of few-shot classification task for a long time. To alleviate this problem, recent researchers build connections between support and query instances through embedding patch features to generate discriminative representations. However, we observe that there exists semantic mismatches (foreground/ background) among these local patches, because the location and size of the target object are not fixed. What is worse, these mismatches result in unreliable similarity confidences, and complex dense connection exacerbates the problem. According to this, we propose a novel Clustered-patch Element Connection (CEC) layer to correct the mismatch problem. The CEC layer leverages Patch Cluster and Element Connection operations to collect and establish reliable connections with high similarity patch features, respectively. Moreover, we propose a CECNet, including CEC layer based attention module and distance metric. The former is utilized to generate a more discriminative representation benefiting from the global clustered-patch features, and the latter is introduced to reliably measure the similarity between pair-features. Extensive experiments demonstrate that our CECNet outperforms the state-of-the-art methods on classification benchmark. Furthermore, our CEC approach can be extended into few-shot segmentation and detection tasks, which achieves competitive performances.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 61 of its 84 references that are in the map. First posted on arXiv 20 Apr 2023.

Builds on

61 of 84 references.

References · 61

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  11. 2016Matching Networks for One Shot Learningcited by 2,246
  12. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
38 more
  1. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  2. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  3. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  4. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  5. 2019A Closer Look at Few-shot Classificationcited by 679
  6. 2016Learning to learn by gradient descent by gradient descentcited by 616
  7. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  8. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  9. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  10. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  11. 2017One-Shot Learning for Semantic Segmentationcited by 337
  12. 2016Learning Convolutional Neural Networks for Graphscited by 314
  13. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  14. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  15. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  16. 2015Diffusion-Convolutional Neural Networkscited by 268
  17. 2017Meta Networkscited by 268
  18. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  19. 2019Cross Attention Network for Few-shot Classificationcited by 218
  20. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  21. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  22. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  23. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  24. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  25. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  26. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  27. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  28. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  29. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  30. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  31. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  32. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  33. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  34. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  35. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  36. 2019PolyTransform: Deep Polygon Transformer for Instance Segmentationcited by 92
  37. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  38. 2019When Does Self-supervision Improve Few-shot Learning?cited by 78

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2024Hyper-3DG: Text-to-3D Gaussian Generation via Hypergraphcited by 21
  2. 2025Slot Attention-based Feature Filtering for Few-Shot Learningcited by 1
  3. 2025Stochastic-based Patch Filtering for Few-Shot Learningcited by 0
  4. 2026SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learningcited by 0