mlsanityData to 14 Oct 2026

Hallucination Improves Few-Shot Object Detection

arXiv 2105.01294 ↗First posted 4 May 2021cs.CVcited by 50

Not on the map. Why?

Abstract (arXiv)

Learning to detect novel objects from few annotated examples is of great practical importance. A particularly challenging yet common regime occurs when there are extremely limited examples (less than three). One critical factor in improving few-shot detection is to address the lack of variation in training data. We propose to build a better model of variation for novel classes by transferring the shared within-class variation from base classes. To this end, we introduce a hallucinator network that learns to generate additional, useful training examples in the region of interest (RoI) feature space, and incorporate it into a modern object detection model. Our approach yields significant performance improvements on two state-of-the-art few-shot detectors with different proposal generation procedures. In particular, we achieve new state of the art in the extremely-few-shot regime on the challenging COCO benchmark.

Key facts. Cited by 50 papers in the map (data through 14 Oct 2026). Builds on 38 of its 51 references that are in the map. First posted on arXiv 4 May 2021.

Builds on

38 of 51 references.

References · 38

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2017Mask R-CNNcited by 7,277
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  10. 2015Fast R-CNNcited by 2,933
  11. 2018YOLOv3: An Incremental Improvementcited by 2,659
  12. 2016Matching Networks for One Shot Learningcited by 2,255
26 more
  1. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  2. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  3. 2017Deformable Convolutional Networkscited by 1,488
  4. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  5. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  6. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 720
  7. 2020Frustratingly Simple Few-Shot Object Detectioncited by 282
  8. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  9. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  10. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  11. 2018Low-Shot Learning from Imaginary Datacited by 181
  12. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  13. 2019Bottom-up Object Detection by Grouping Extreme and Center Pointscited by 156
  14. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  15. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  16. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  17. 2018RepMet: Representative-based metric learning for classification and one-shot object detectioncited by 85
  18. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  19. 2021Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detectioncited by 79
  20. 2018LSTD: A Low-Shot Transfer Detector for Object Detectioncited by 77
  21. 2019One-Shot Object Detection with Co-Attention and Co-Excitationcited by 67
  22. 2018Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networkscited by 35
  23. 2020OS2D: One-Stage One-Shot Object Detection by Matching Anchor Featurescited by 35
  24. 2020Restoring Negative Information in Few-Shot Object Detectioncited by 28
  25. 2017Few-Example Object Detection with Model Communicationcited by 12
  26. 2020Cooperating RPN's Improve Few-Shot Object Detectioncited by 12

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 23; 2023: 15; 2024: 4; 2025: 2.

50 papers.

Sort:

By area:

  1. 2022SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detectioncited by 74
  2. 2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
  3. 2022Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitationcited by 48
  4. 2021Few-Shot Object Detection via Association and DIscriminationcited by 39
  5. 2023Explore the Power of Synthetic Data on Few-shot Object Detectioncited by 38
  6. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 29
  7. 2021Few-shot Keypoint Detection with Uncertainty Learning for Unseen Speciescited by 27
  8. 2022Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localizationcited by 24
  9. 2023Few-Shot Object Detection via Variational Feature Aggregationcited by 22
  10. 2023Generating Features with Increased Crop-related Diversity for Few-Shot Object Detectioncited by 21
  11. 2022FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-trainingcited by 20
  12. 2023Hallucination Improves the Performance of Unsupervised Visual Representation Learningcited by 16
38 more
  1. 2022Semantic-aligned Fusion Transformer for One-shot Object Detectioncited by 13
  2. 2022Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspectivecited by 13
  3. 2021AirDet: Few-Shot Detection without Fine-tuning for Autonomous Explorationcited by 12
  4. 2022Efficient Few-Shot Object Detection via Knowledge Inheritancecited by 12
  5. 2022Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detectioncited by 12
  6. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  7. 2022Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Promptingcited by 11
  8. 2022Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detectioncited by 11
  9. 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
  10. 2022Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectorscited by 10
  11. 2022Mobile Robot Manipulation using Pure Object Detectioncited by 8
  12. 2022Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparisoncited by 8
  13. 2023From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detectioncited by 8
  14. 2024Meta-Point Learning and Refining for Category-Agnostic Pose Estimationcited by 7
  15. 2021A Survey of Deep Learning for Low-Shot Object Detectioncited by 6
  16. 2025Multi-Perspective Data Augmentation for Few-shot Object Detectioncited by 6
  17. 2023The Art of Camouflage: Few-Shot Learning for Animal Detection and Segmentationcited by 5
  18. 2022Few-shot Object Detection with Refined Contrastive Learningcited by 4
  19. 2023Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detectioncited by 4
  20. 2023ECEA: Extensible Co-Existing Attention for Few-Shot Object Detectioncited by 4
  21. 2022Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representationscited by 3
  22. 2022Exploring Effective Knowledge Transfer for Few-shot Object Detectioncited by 3
  23. 2023An Effective Crop-Paste Pipeline for Few-shot Object Detectioncited by 3
  24. 2023Few-Shot Object Detection via Synthetic Features with Optimal Transportcited by 3
  25. 2022Incremental Few-Shot Learning via Implanting and Compressingcited by 2
  26. 2022Proposal Distribution Calibration for Few-Shot Object Detectioncited by 2
  27. 2023TIDE: Test Time Few Shot Object Detectioncited by 2
  28. 2024PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detectioncited by 2
  29. 2024A Closer Look at Data Augmentation Strategies for Finetuning-Based Low/Few-Shot Object Detectioncited by 2
  30. 2022Learning Prototype via Placeholder for Zero-shot Recognitioncited by 1
  31. 2022A Unified Framework with Meta-dropout for Few-shot Learningcited by 1
  32. 2022A Comparative Attention Framework for Better Few-Shot Object Detection on Aerial Imagescited by 1
  33. 2023Decoupled DETR For Few-shot Object Detectioncited by 1
  34. 2024Learning with Instance-Dependent Noisy Labels by Anchor Hallucination and Hard Sample Label Correctioncited by 1
  35. 2025FSP-DETR: Few-Shot Prototypical Parasitic Ova Detectioncited by 1
  36. 2022Few-Shot Object Detection with Proposal Balance Refinementcited by 0
  37. 2023Explore the Power of Dropout on Few-shot Learningcited by 0
  38. 2023GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detectioncited by 0