Beyond Few-shot Object Detection: A Detailed Survey
Not on the map. Why?
Abstract (arXiv)
Object detection is a critical field in computer vision focusing on accurately identifying and locating specific objects in images or videos. Traditional methods for object detection rely on large labeled training datasets for each object category, which can be time-consuming and expensive to collect and annotate. To address this issue, researchers have introduced few-shot object detection (FSOD) approaches that merge few-shot learning and object detection principles. These approaches allow models to quickly adapt to new object categories with only a few annotated samples. While traditional FSOD methods have been studied before, this survey paper comprehensively reviews FSOD research with a specific focus on covering different FSOD settings such as standard FSOD, generalized FSOD, incremental FSOD, open-set FSOD, and domain adaptive FSOD. These approaches play a vital role in reducing the reliance on extensive labeled datasets, particularly as the need for efficient machine learning models continues to rise. This survey paper aims to provide a comprehensive understanding of the above-mentioned few-shot settings and explore the methodologies for each FSOD task. It thoroughly compares state-of-the-art methods across different FSOD settings, analyzing them in detail based on their evaluation protocols. Additionally, it offers insights into their applications, challenges, and potential future directions in the evolving field of object detection with limited data.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 45 of its 239 references that are in the map. First posted on arXiv 26 Aug 2024.
Builds on
45 of 239 references.
References · 45
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
- 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2018YOLOv3: An Incremental Improvementcited by 2,652
- 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
- 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
- 2019Objects as Pointscited by 1,172
- 2019A Closer Look at Few-shot Classificationcited by 679
- 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
- 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
- 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
33 more
- 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
- 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
- 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
- 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
- 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
- 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
- 2016Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?cited by 194
- 2021The iWildCam 2021 Competition Datasetcited by 77
- 2019One-Shot Object Detection with Co-Attention and Co-Excitationcited by 67
- 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
- 2021Few-Shot Object Detection via Association and DIscriminationcited by 39
- 2023Revisiting Few-Shot Object Detection with Vision-Language Modelscited by 32
- 2020Restoring Negative Information in Few-Shot Object Detectioncited by 28
- 2023Few-shot Class-incremental Learning for Classification and Object Detection: A Surveycited by 25
- 2021Class-Incremental Few-Shot Object Detectioncited by 13
- 2023Detect Everything with Few Examplescited by 13
- 2020Cooperating RPN's Improve Few-Shot Object Detectioncited by 12
- 2022Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Promptingcited by 11
- 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
- 2024Fine-Grained Prototypes Distillation for Few-Shot Object Detectioncited by 10
- 2022Hierarchical Few-Shot Object Detection: Problem, Benchmark and Methodcited by 8
- 2022Towards Generalized Few-Shot Open-Set Object Detectioncited by 8
- 2021Towards Generalized and Incremental Few-Shot Object Detectioncited by 7
- 2021A Survey of Deep Learning for Low-Shot Object Detectioncited by 6
- 2022Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learningcited by 6
- 2019Oktoberfest Food Datasetcited by 5
- 2021Dynamic Relevance Learning for Few-Shot Object Detectioncited by 5
- 2020Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddingscited by 4
- 2020Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detectioncited by 4
- 2023ECEA: Extensible Co-Existing Attention for Few-Shot Object Detectioncited by 4
- 2021Instant Response Few-shot Object Detection with Meta Strategy and Explicit Localization Inferencecited by 2
- 2022MINI: Mining Implicit Novel Instances for Few-Shot Object Detectioncited by 2
- 2024Few-Shot Object Detection with Sparse Context Transformerscited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.