mlsanityData to 7 Oct 2026

Dual-Awareness Attention for Few-Shot Object Detection

arXiv 2102.12152 ↗First posted 24 Feb 2021cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

While recent progress has significantly boosted few-shot classification (FSC) performance, few-shot object detection (FSOD) remains challenging for modern learning systems. Existing FSOD systems follow FSC approaches, ignoring critical issues such as spatial variability and uncertain representations, and consequently result in low performance. Observing this, we propose a novel Dual-Awareness Attention (DAnA) mechanism that enables networks to adaptively interpret the given support images. DAnA transforms support images into query-position-aware (QPA) features, guiding detection networks precisely by assigning customized support information to each local region of the query. In addition, the proposed DAnA component is flexible and adaptable to multiple existing object detection frameworks. By adopting DAnA, conventional object detection networks, Faster R-CNN and RetinaNet, which are not designed explicitly for few-shot learning, reach state-of-the-art performance in FSOD tasks. In comparison with previous methods, our model significantly increases the performance by 47% (+6.9 AP), showing remarkable ability under various evaluation settings.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 42 of its 55 references that are in the map. First posted on arXiv 24 Feb 2021.

Builds on

42 of 55 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2015Fast R-CNNcited by 2,930
  10. 2017Non-local Neural Networkscited by 2,290
  11. 2016Matching Networks for One Shot Learningcited by 2,246
  12. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
30 more
  1. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  2. 2019Objects as Pointscited by 1,172
  3. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  4. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  5. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  6. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  7. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  8. 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
  9. 2017Convolutional Sequence to Sequence Learningcited by 550
  10. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  11. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  12. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  13. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  14. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  15. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  16. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  17. 2019Local Relation Networks for Image Recognitioncited by 210
  18. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  19. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  20. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  21. 2020Disentangled Non-Local Neural Networkscited by 132
  22. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  23. 2020Incremental Few-Shot Object Detectioncited by 102
  24. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  25. 2019Prototype Rectification for Few-Shot Learningcited by 96
  26. 2018RepMet: Representative-based metric learning for classification and one-shot object detectioncited by 85
  27. 2018LSTD: A Low-Shot Transfer Detector for Object Detectioncited by 77
  28. 2019An Empirical Study of Spatial Attention Mechanisms in Deep Networkscited by 58
  29. 2020FGN: Fully Guided Network for Few-Shot Instance Segmentationcited by 46
  30. 2019SPA-GAN: Spatial Attention GAN for Image-to-Image Translationcited by 43

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 12; 2023: 10; 2024: 0; 2025: 2; 2026: 1.

29 papers.

Sort:

By area:

  1. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  2. 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
  3. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  4. 2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
  5. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 28
  6. 2022AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detectioncited by 25
  7. 2022Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localizationcited by 24
  8. 2022Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detectioncited by 23
  9. 2022TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learningcited by 16
  10. 2022Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometrycited by 12
  11. 2022Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detectioncited by 12
  12. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
17 more
  1. 2022Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Promptingcited by 11
  2. 2022Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectorscited by 10
  3. 2023NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forgingcited by 10
  4. 2023TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentationcited by 9
  5. 2022Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparisoncited by 8
  6. 2022Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learningcited by 6
  7. 2023Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detectioncited by 4
  8. 2023Attacking Important Pixels for Anchor-free Detectorscited by 3
  9. 2023Improving Multi-Person Pose Tracking with A Confidence Networkcited by 3
  10. 2021Instant Response Few-shot Object Detection with Meta Strategy and Explicit Localization Inferencecited by 2
  11. 2025Efficient Dual-domain Image Dehazing with Haze Prior Perceptioncited by 2
  12. 2022Few-Shot Object Detection in Unseen Domainscited by 0
  13. 2023Adaptive Base-class Suppression and Prior Guidance Network for One-Shot Object Detectioncited by 0
  14. 2023Re-Scoring Using Image-Language Similarity for Few-Shot Object Detectioncited by 0
  15. 2023SKU-Patch: Towards Efficient Instance Segmentation for Unseen Objects in Auto-Storecited by 0
  16. 2025Few-Shot Object Detection via Spatial-Channel State Space Modelcited by 0
  17. 2026LV-OSD: Language-Vision-Complementary Open-Set Object Detectioncited by 0