mlsanityData to 7 Oct 2026

Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

arXiv 2007.09384 ↗First posted 18 Jul 2020cs.CVcited by 116

Not on the map. Why?

Abstract (arXiv)

Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited. Unlike previous attempts that exploit few-shot classification techniques to facilitate FSOD, this work highlights the necessity of handling the problem of scale variations, which is challenging due to the unique sample distribution. To this end, we propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD. It generates multi-scale positive samples as object pyramids and refines the prediction at various scales. We demonstrate its advantage by integrating it as an auxiliary branch to the popular architecture of Faster R-CNN with FPN, delivering a strong FSOD solution. Several experiments are conducted on PASCAL VOC and MS COCO, and the proposed approach achieves state of the art results and significantly outperforms other counterparts, which shows its effectiveness. Code is available at https://github.com/jiaxi-wu/MPSR.

Key facts. Cited by 116 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 41; 2023: 27; 2024: 12; 2025: 8; 2026: 2.

116 papers.

Sort:

By area:

  1. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 177
  2. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  3. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  4. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  5. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  6. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  7. 2021Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detectioncited by 79
  8. 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
  9. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  10. 2022Few-shot Object Counting with Similarity-Aware Feature Enhancementcited by 62
  11. 2021Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignmentcited by 57
  12. 2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networkscited by 55
38 more
  1. 2022Few-shot Object Counting and Detectioncited by 55
  2. 2021Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Typescited by 54
  3. 2021Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detectioncited by 53
  4. 2021Hallucination Improves Few-Shot Object Detectioncited by 50
  5. 2022Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitationcited by 48
  6. 2021Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitationcited by 44
  7. 2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
  8. 2021Label, Verify, Correct: A Simple Few Shot Object Detection Methodcited by 43
  9. 2021Few-Shot Object Detection via Association and DIscriminationcited by 39
  10. 2023Explore the Power of Synthetic Data on Few-shot Object Detectioncited by 38
  11. 2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
  12. 2023Revisiting Few-Shot Object Detection with Vision-Language Modelscited by 32
  13. 2021Dual-Awareness Attention for Few-Shot Object Detectioncited by 29
  14. 2022Real-time Object Detection for Streaming Perceptioncited by 29
  15. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 28
  16. 2022AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detectioncited by 25
  17. 2022Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localizationcited by 24
  18. 2023Few-Shot Object Detection via Variational Feature Aggregationcited by 22
  19. 2023DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detectioncited by 21
  20. 2023Generating Features with Increased Crop-related Diversity for Few-Shot Object Detectioncited by 21
  21. 2022FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-trainingcited by 20
  22. 2022iFS-RCNN: An Incremental Few-shot Instance Segmentercited by 19
  23. 2021LARGE: Latent-Based Regression through GAN Semanticscited by 17
  24. 2022Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learningcited by 14
  25. 2022Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detectioncited by 14
  26. 2022Semantic-aligned Fusion Transformer for One-shot Object Detectioncited by 13
  27. 2022Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspectivecited by 13
  28. 2021AirDet: Few-Shot Detection without Fine-tuning for Autonomous Explorationcited by 12
  29. 2022Efficient Few-Shot Object Detection via Knowledge Inheritancecited by 12
  30. 2022Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detectioncited by 12
  31. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  32. 2022Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Promptingcited by 11
  33. 2022Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detectioncited by 11
  34. 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
  35. 2022Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectorscited by 10
  36. 2022Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detectioncited by 10
  37. 2023NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forgingcited by 10
  38. 2024Fine-Grained Prototypes Distillation for Few-Shot Object Detectioncited by 10

50 most cited of 116 All 116 (JSON)