Data to 14 Oct 2026

Few-shot Object Detection via Feature Reweighting

arXiv 1812.01866 ↗First posted 5 Dec 2018cs.CVcited by 265

Not on the map. Why?

Abstract (arXiv)

Conventional training of a deep CNN based object detector demands a large number of bounding box annotations, which may be unavailable for rare categories. In this work we develop a few-shot object detector that can learn to detect novel objects from only a few annotated examples. Our proposed model leverages fully labeled base classes and quickly adapts to novel classes, using a meta feature learner and a reweighting module within a one-stage detection architecture. The feature learner extracts meta features that are generalizable to detect novel object classes, using training data from base classes with sufficient samples. The reweighting module transforms a few support examples from the novel classes to a global vector that indicates the importance or relevance of meta features for detecting the corresponding objects. These two modules, together with a detection prediction module, are trained end-to-end based on an episodic few-shot learning scheme and a carefully designed loss function. Through extensive experiments we demonstrate that our model outperforms well-established baselines by a large margin for few-shot object detection, on multiple datasets and settings. We also present analysis on various aspects of our proposed model, aiming to provide some inspiration for future few-shot detection works.

Key facts. Cited by 265 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 61; 2022: 71; 2023: 57; 2024: 37; 2025: 22; 2026: 17.

265 papers.

Sort:

By area:

2021Grounded Language-Image Pre-trainingcited by 1,156
2022Visual Prompting via Image Inpaintingcited by 250
2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
2021Learning To Count Everythingcited by 150
2022PromptDet: Towards Open-vocabulary Detection using Uncurated Imagescited by 133
2025GR-3 Technical Reportcited by 111
2021Learning Open-World Object Proposals without Learning to Classifycited by 109
2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
2022Self-Support Few-Shot Semantic Segmentationcited by 96
2023Vision-Language Models in Remote Sensing: Current Progress and Future Trendscited by 93
2021Generalized Few-Shot Object Detection without Forgettingcited by 88

38 more

2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
2021Temporal-Relational CrossTransformers for Few-Shot Action Recognitioncited by 84
2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
2021Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detectioncited by 79
2022CounTR: Transformer-based Generalised Visual Countingcited by 79
2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
2022Few-Shot Object Detection with Fully Cross-Transformercited by 64
2022Few-shot Object Counting with Similarity-Aware Feature Enhancementcited by 62
2024CountGD: Multi-Modal Open-World Countingcited by 59
2022Accelerating DETR Convergence via Semantic-Aligned Matchingcited by 58
2021Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignmentcited by 57
2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networkscited by 55
2022Few-shot Object Counting and Detectioncited by 55
2021Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detectioncited by 53
2023Multi-Modal Classifiers for Open-Vocabulary Object Detectioncited by 53
2021Hallucination Improves Few-Shot Object Detectioncited by 50
2021Incremental Few-Shot Instance Segmentationcited by 49
2021A Simple Long-Tailed Recognition Baseline via Vision-Language Modelcited by 49
2022Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitationcited by 48
2023A Survey on Few-Shot Class-Incremental Learningcited by 48
2023Multi-modal Queried Object Detection in the Wildcited by 47
2021Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitationcited by 44
2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
2021Label, Verify, Correct: A Simple Few Shot Object Detection Methodcited by 43
2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
2022Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervisioncited by 41
2021Few-Shot Object Detection via Association and DIscriminationcited by 39
2023Explore the Power of Synthetic Data on Few-shot Object Detectioncited by 38
2021Learning to Detect Every Thing in an Open Worldcited by 37
2021A Survey of Self-Supervised and Few-Shot Object Detectioncited by 35
2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
2021Wanderlust: Online Continual Object Detection in the Real Worldcited by 34
2023Revisiting Few-Shot Object Detection with Vision-Language Modelscited by 32
2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Miningcited by 30

50 most cited of 265 All 265 (JSON)