mlsanityData to 14 Oct 2026

Few-Shot Object Detection: A Comprehensive Survey

arXiv 2112.11699 ↗First posted 22 Dec 2021cs.CV cs.LGcited by 29

Not on the map. Why?

Abstract (arXiv)

Humans are able to learn to recognize new objects even from a few examples. In contrast, training deep-learning-based object detectors requires huge amounts of annotated data. To avoid the need to acquire and annotate these huge amounts of data, few-shot object detection aims to learn from few object instances of new categories in the target domain. In this survey, we provide an overview of the state of the art in few-shot object detection. We categorize approaches according to their training scheme and architectural layout. For each type of approaches, we describe the general realization as well as concepts to improve the performance on novel categories. Whenever appropriate, we give short takeaways regarding these concepts in order to highlight the best ideas. Eventually, we introduce commonly used datasets and their evaluation protocols and analyze reported benchmark results. As a result, we emphasize common challenges in evaluation and identify the most promising current trends in this emerging field of few-shot object detection.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 91 of its 153 references that are in the map. First posted on arXiv 22 Dec 2021.

Builds on

91 of 153 references.

References · 91

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  8. 2017Mask R-CNNcited by 7,277
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  11. 2017Squeeze-and-Excitation Networkscited by 4,789
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
38 more
  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  2. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2018YOLOv3: An Incremental Improvementcited by 2,659
  5. 2016Pyramid Scene Parsing Networkcited by 2,479
  6. 2017Non-local Neural Networkscited by 2,293
  7. 2016Matching Networks for One Shot Learningcited by 2,255
  8. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  9. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  10. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  11. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  12. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  13. 2019Objects as Pointscited by 1,175
  14. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  15. 2018Efficient Lifelong Learning with A-GEMcited by 1,058
  16. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  17. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  18. 2019Large Scale Incremental Learningcited by 732
  19. 2020A Survey on Visual Transformercited by 654
  20. 2018End-to-End Incremental Learningcited by 597
  21. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 544
  22. 2018Object Detection with Deep Learning: A Reviewcited by 528
  23. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  24. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  25. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 356
  26. 2020Frustratingly Simple Few-Shot Object Detectioncited by 282
  27. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  28. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  29. 2018Zero-Shot Object Detectioncited by 189
  30. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  31. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  32. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  33. 2019Exploring Object Relation in Mean Teacher for Cross-Domain Detectioncited by 137
  34. 2020Harmonizing Transferability and Discriminability for Adapting Object Detectorscited by 126
  35. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  36. 2020Cross-domain Detection via Graph-induced Prototype Alignmentcited by 109
  37. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  38. 2020Incremental Few-Shot Object Detectioncited by 102

50 most cited of 91 All 91 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 7; 2024: 7; 2025: 9; 2026: 5.

29 papers.

Sort:

By area:

  1. 2023Towards Open Vocabulary Learning: A Surveycited by 166
  2. 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
  3. 2023Revisiting Few-Shot Object Detection with Vision-Language Modelscited by 32
  4. 2025Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detectioncited by 15
  5. 2023Detect Everything with Few Examplescited by 14
  6. 2024Few-Shot Object Detection: Research Advances and Challengescited by 11
  7. 2025Logits DeConfusion with CLIP for Few-Shot Learningcited by 11
  8. 2023Identification of Novel Classes for Improving Few-Shot Object Detectioncited by 7
  9. 2024Exploring Robust Features for Few-Shot Object Detection in Satellite Imagerycited by 7
  10. 2023Improved Region Proposal Network for Enhanced Few-Shot Object Detectioncited by 5
  11. 2024Few-Shot Learning for Annotation-Efficient Nucleus Instance Segmentationcited by 3
  12. 2026Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detectioncited by 3
17 more
  1. 2023On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrievalcited by 2
  2. 2024Few-Shot Object Detection with Sparse Context Transformerscited by 2
  3. 2025Analyzing the Impact of Low-Rank Adaptation for Cross-Domain Few-Shot Object Detection in Aerial Imagescited by 2
  4. 2025Can Foundation Models Generalise the Presentation Attack Detection Capabilities on ID Cards?cited by 2
  5. 2025Few-Shot Learning in Video and 3D Object Detection: A Surveycited by 2
  6. 2026DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detectioncited by 2
  7. 2023Decoupled DETR For Few-shot Object Detectioncited by 1
  8. 2025FSP-DETR: Few-Shot Prototypical Parasitic Ova Detectioncited by 1
  9. 2026Rethinking Prototype-based Similarity Learning for Few-Shot Object Detectioncited by 1
  10. 2022Automatic Bounding Box Annotation with Small Training Data Sets for Industrial Manufacturingcited by 0
  11. 2024InfRS: Incremental Few-Shot Object Detection in Remote Sensing Imagescited by 0
  12. 2024Cognitive Manipulation: Semi-supervised Visual Representation and Classroom-to-real Reinforcement Learning for Assembly in Semi-structured Environmentscited by 0
  13. 2025Exploring Few-Shot Object Detection on Blood Smear Images: A Case Study of Leukocytes and Schistocytescited by 0
  14. 2025Visual Trajectory Prediction of Vessels for Inland Navigationcited by 0
  15. 2025Enhancing Early Alzheimer Disease Detection through Big Data and Ensemble Few-Shot Learningcited by 0
  16. 2026Evaluating Few-Shot Pill Recognition Under Visual Domain Shiftcited by 0
  17. 2026Personalized Object Identification and Localization via In-Context Inference with Vision-Language Modelscited by 0