mlsanityData to 7 Oct 2026

Universal-Prototype Enhancing for Few-Shot Object Detection

arXiv 2103.01077 ↗First posted 1 Mar 2021cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

Few-shot object detection (FSOD) aims to strengthen the performance of novel object detection with few labeled samples. To alleviate the constraint of few samples, enhancing the generalization ability of learned features for novel objects plays a key role. Thus, the feature learning process of FSOD should focus more on intrinsical object characteristics, which are invariant under different visual changes and therefore are helpful for feature generalization. Unlike previous attempts of the meta-learning paradigm, in this paper, we explore how to enhance object features with intrinsical characteristics that are universal across different object categories. We propose a new prototype, namely universal prototype, that is learned from all object categories. Besides the advantage of characterizing invariant characteristics, the universal prototypes alleviate the impact of unbalanced object categories. After enhancing object features with the universal prototypes, we impose a consistency loss to maximize the agreement between the enhanced features and the original ones, which is beneficial for learning invariant object characteristics. Thus, we develop a new framework of few-shot object detection with universal prototypes ({FSOD}^{up}) that owns the merit of feature generalization towards novel objects. Experimental results on PASCAL VOC and MS COCO show the effectiveness of {FSOD}^{up}. Particularly, for the 1-shot case of VOC Split2, {FSOD}^{up} outperforms the baseline by 6.8% in terms of mAP.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 32 of its 40 references that are in the map. First posted on arXiv 1 Mar 2021.

Builds on

32 of 40 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  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. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  10. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  11. 2015Fast R-CNNcited by 2,930
  12. 2016Matching Networks for One Shot Learningcited by 2,246
20 more
  1. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  2. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  3. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  5. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  6. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  7. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  8. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  9. 2019A Baseline for Few-Shot Image Classificationcited by 298
  10. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  11. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  12. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  13. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  14. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  15. 2019Learning Data Augmentation Strategies for Object Detectioncited by 139
  16. 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
  17. 2019Prototype Rectification for Few-Shot Learningcited by 96
  18. 2018RepMet: Representative-based metric learning for classification and one-shot object detectioncited by 85
  19. 2019TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learningcited by 32
  20. 2020Context-Transformer: Tackling Object Confusion for Few-Shot Detectioncited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 15; 2023: 11; 2024: 5; 2025: 3; 2026: 6.

43 papers.

Sort:

By area:

  1. 2023Multi-modal Queried Object Detection in the Wildcited by 47
  2. 2023Explore the Power of Synthetic Data on Few-shot Object Detectioncited by 38
  3. 2023Revisiting Few-Shot Object Detection with Vision-Language Modelscited by 32
  4. 2021Few-Shot Object Detection: A Comprehensive Surveycited by 28
  5. 2023Few-Shot Object Detection via Variational Feature Aggregationcited by 22
  6. 2023Generating Features with Increased Crop-related Diversity for Few-Shot Object Detectioncited by 21
  7. 2022FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-trainingcited by 20
  8. 2025Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentationcited by 16
  9. 2022Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detectioncited by 14
  10. 2024Commonsense Prototype for Outdoor Unsupervised 3D Object Detectioncited by 13
  11. 2021AirDet: Few-Shot Detection without Fine-tuning for Autonomous Explorationcited by 12
  12. 2022Efficient Few-Shot Object Detection via Knowledge Inheritancecited by 12
31 more
  1. 2023Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentationcited by 12
  2. 2022Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Promptingcited by 11
  3. 2022Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detectioncited by 11
  4. 2022Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detectioncited by 10
  5. 2024AirShot: Efficient Few-Shot Detection for Autonomous Explorationcited by 10
  6. 2022Mobile Robot Manipulation using Pure Object Detectioncited by 8
  7. 2022Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparisoncited by 8
  8. 2022Towards Generalized Few-Shot Open-Set Object Detectioncited by 8
  9. 2021A Survey of Deep Learning for Low-Shot Object Detectioncited by 6
  10. 2025Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detectioncited by 6
  11. 2022Function-words Enhanced Attention Networks for Few-Shot Inverse Relation Classificationcited by 5
  12. 2022Few-shot Object Detection with Refined Contrastive Learningcited by 4
  13. 2022Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representationscited by 3
  14. 2023An Effective Crop-Paste Pipeline for Few-shot Object Detectioncited by 3
  15. 2023Multi-Content Interaction Network for Few-Shot Segmentationcited by 2
  16. 2024PS-TTL: Prototype-based Soft-labels and Test-Time Learning for Few-shot Object Detectioncited by 2
  17. 2026DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detectioncited by 2
  18. 2026A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helpscited by 2
  19. 2022A Unified Framework for Attention-Based Few-Shot Object Detectioncited by 1
  20. 2022A Comparative Attention Framework for Better Few-Shot Object Detection on Aerial Imagescited by 1
  21. 2023Decoupled DETR For Few-shot Object Detectioncited by 1
  22. 2024Detect an Object At Once without Fine-tuningcited by 1
  23. 2024Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detectioncited by 1
  24. 2022Automatic Bounding Box Annotation with Small Training Data Sets for Industrial Manufacturingcited by 0
  25. 2023SKU-Patch: Towards Efficient Instance Segmentation for Unseen Objects in Auto-Storecited by 0
  26. 2023GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detectioncited by 0
  27. 2025Efficient Masked Attention Transformer for Few-Shot Classification and Segmentationcited by 0
  28. 2026Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoningcited by 0
  29. 2026Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learningcited by 0
  30. 2026Heuristic-inspired Reasoning Priors Facilitate Data-Efficient Referring Object Detectioncited by 0
  31. 2026Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detectioncited by 0