mlsanityData to 7 Oct 2026

Frustratingly Simple Few-Shot Object Detection

arXiv 2003.06957 ↗First posted 16 Mar 2020cs.CVcited by 280

Not on the map. Why?

Abstract (arXiv)

Detecting rare objects from a few examples is an emerging problem. Prior works show meta-learning is a promising approach. But, fine-tuning techniques have drawn scant attention. We find that fine-tuning only the last layer of existing detectors on rare classes is crucial to the few-shot object detection task. Such a simple approach outperforms the meta-learning methods by roughly 2~20 points on current benchmarks and sometimes even doubles the accuracy of the prior methods. However, the high variance in the few samples often leads to the unreliability of existing benchmarks. We revise the evaluation protocols by sampling multiple groups of training examples to obtain stable comparisons and build new benchmarks based on three datasets: PASCAL VOC, COCO and LVIS. Again, our fine-tuning approach establishes a new state of the art on the revised benchmarks. The code as well as the pretrained models are available at https://github.com/ucbdrive/few-shot-object-detection.

Key facts. Cited by 280 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 59; 2022: 72; 2023: 58; 2024: 37; 2025: 31; 2026: 23.

280 papers.

Sort:

By area:

  1. 2021Grounded Language-Image Pre-trainingcited by 1,147
  2. 2021Towards Open World Object Detectioncited by 297
  3. 2022GLIPv2: Unifying Localization and Vision-Language Understandingcited by 275
  4. 2022Visual Prompting via Image Inpaintingcited by 248
  5. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  6. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  7. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  8. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  9. 2022ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Modelscited by 141
  10. 2021OW-DETR: Open-world Detection Transformercited by 129
  11. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  12. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
38 more
  1. 2022CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Drivingcited by 100
  2. 2023Vision-Language Models in Remote Sensing: Current Progress and Future Trendscited by 93
  3. 2021Generalized Few-Shot Object Detection without Forgettingcited by 88
  4. 2021Class-agnostic Object Detection with Multi-modal Transformercited by 85
  5. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  6. 2021Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detectioncited by 79
  7. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  8. 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
  9. 2023Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustmentcited by 75
  10. 2021Relational Embedding for Few-Shot Classificationcited by 74
  11. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  12. 2021Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignmentcited by 57
  13. 2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networkscited by 55
  14. 2022Few-shot Object Counting and Detectioncited by 55
  15. 2021Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Typescited by 54
  16. 2021Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detectioncited by 53
  17. 2023Multi-Modal Classifiers for Open-Vocabulary Object Detectioncited by 53
  18. 2021Spatio-temporal Relation Modeling for Few-shot Action Recognitioncited by 52
  19. 2021Hallucination Improves Few-Shot Object Detectioncited by 50
  20. 2021Incremental Few-Shot Instance Segmentationcited by 49
  21. 2022Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitationcited by 48
  22. 2023Multi-modal Queried Object Detection in the Wildcited by 47
  23. 2021Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitationcited by 44
  24. 2022Towards Open-Set Object Detection and Discoverycited by 44
  25. 2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
  26. 2021Label, Verify, Correct: A Simple Few Shot Object Detection Methodcited by 43
  27. 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
  28. 2022UC-OWOD: Unknown-Classified Open World Object Detectioncited by 40
  29. 2021On Model Calibration for Long-Tailed Object Detection and Instance Segmentationcited by 39
  30. 2021Few-Shot Object Detection via Association and DIscriminationcited by 39
  31. 2023Point, Segment and Count: A Generalized Framework for Object Countingcited by 39
  32. 2022Expanding Low-Density Latent Regions for Open-Set Object Detectioncited by 38
  33. 2023Explore the Power of Synthetic Data on Few-shot Object Detectioncited by 38
  34. 2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
  35. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  36. 2021Wanderlust: Online Continual Object Detection in the Real Worldcited by 34
  37. 2021MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detectioncited by 33
  38. 2023Revisiting Few-Shot Object Detection with Vision-Language Modelscited by 32

50 most cited of 280 All 280 (JSON)