mlsanityData to 7 Oct 2026

Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning

arXiv 2208.07039 ↗First posted 15 Aug 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Few-shot object detection (FSOD) aims to classify and detect few images of novel categories. Existing meta-learning methods insufficiently exploit features between support and query images owing to structural limitations. We propose a hierarchical attention network with sequentially large receptive fields to fully exploit the query and support images. In addition, meta-learning does not distinguish the categories well because it determines whether the support and query images match. In other words, metric-based learning for classification is ineffective because it does not work directly. Thus, we propose a contrastive learning method called meta-contrastive learning, which directly helps achieve the purpose of the meta-learning strategy. Finally, we establish a new state-of-the-art network, by realizing significant margins. Our method brings 2.3, 1.0, 1.3, 3.4 and 2.4% AP improvements for 1-30 shots object detection on COCO dataset. Our code is available at: https://github.com/infinity7428/hANMCL

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 37 of its 45 references that are in the map. First posted on arXiv 15 Aug 2022.

Builds on

37 of 45 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2020Supervised Contrastive Learningcited by 2,803
  10. 2016Matching Networks for One Shot Learningcited by 2,246
  11. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  12. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
25 more
  1. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  2. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
  3. 2022How Do Vision Transformers Work?cited by 305
  4. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  5. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  6. 2022Visual Attention Networkcited by 210
  7. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  8. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  9. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  10. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  11. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  12. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  13. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  14. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  15. 2019One-Shot Object Detection with Co-Attention and Co-Excitationcited by 67
  16. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  17. 2021Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignmentcited by 57
  18. 2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networkscited by 55
  19. 2021Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detectioncited by 53
  20. 2020FGN: Fully Guided Network for Few-Shot Instance Segmentationcited by 46
  21. 2021Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitationcited by 44
  22. 2021Few-Shot Object Detection via Association and DIscriminationcited by 39
  23. 2021Dual-Awareness Attention for Few-Shot Object Detectioncited by 29
  24. 2021LibFewShot: A Comprehensive Library for Few-shot Learningcited by 21
  25. 2020Cooperating RPN's Improve Few-Shot Object Detectioncited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2022Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localizationcited by 24
  2. 2024Beyond Few-shot Object Detection: A Detailed Surveycited by 2
  3. 2024Few-Shot Medical Image Segmentation with Large Kernel Attentioncited by 1
  4. 2025Understanding Trade offs When Conditioning Synthetic Datacited by 1
  5. 2026Practical Insights into Semi-Supervised Object Detection Approachescited by 1
  6. 2023Adaptive Base-class Suppression and Prior Guidance Network for One-Shot Object Detectioncited by 0