Few-Shot Object Detection

Ask about this topic

Overview

Few-shot object detection studies how to locate new object classes when only a few labeled examples are available, which matters when collecting annotations is costly or new categories appear often. Common approaches fine-tune pretrained detectors, compare query regions with support-image prototypes, or use meta-learning; newer methods also transfer vision-language model features and augment scarce data with synthetic images. Evaluation often uses 1-, 5-, or 10-shot settings on benchmarks such as COCO, as well as cross-domain tests in industrial, medical, and remote-sensing images. A central challenge is that strong class recognition does not guarantee accurate localization under domain shift, while aggressive adaptation or synthetic data can overfit or introduce misleading cues.

Latest papers

CardsList

27 papers1 paper in the last four weeks, down 75% on the four weeks before. 0.0% of all new papers.

  1. Where, How, and When: Query-Guided Grounding for Video Understanding

    Oct 15, 2026Yogesh KumarVideo Moment RetrievalTemporal Video Grounding

    Indian Institute of Technology Jodhpur Department of Computer Science and Engineering

  2. SetOPD: From Few Visual Exemplars to Multimodal Candidate Sets for Remote-Sensing Open-Prompt Detection

    Sep 26, 2026Jinlong Hu, Yi Zhang, Zhiqi Xia +2Multimodal Object DetectionOpen-Vocabulary Object Detection

    Wuhan University · Institute of Seismology, China Earthquake Administration

  3. Semantically-Guided Domain Randomization for Industrial Object Detection in Low-Image-Budget Regimes

    Sep 22, 2026Jose Moises Araya-Martinez, Gautham Mohan, Jens LambrechtDomain RandomizationSynthetic Data Augmentation

    Electrical Engineering and Computer Science TU Berlin Berlin, Germany · Electrical Engineering University of Stuttgart Stuttgart, Germany · Institute for Cognitive Robotics TU Braunschweig Braunschweig, Germany

  4. Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Adaptation of Vision-Language Models

    Sep 10, 2026Gautam Rajendrakumar Gare, Siyi Li, Hewei Wang +5Few-Shot Object DetectionFew-Shot Domain Adaptation

    Carnegie Mellon University · Apple

  5. ProtoRAG: Prototype-Based Retrieval Augmentation for Few-Shot Fine-Grained Remote Sensing Object Detection

    Sep 5, 2026Jian Wang, Yuxiang Hong, Chufeng Zhou +2Few-Shot Object DetectionMemory-Augmented VLMs

    Wuhan University, Wuhan, China · East China Normal University, Shanghai, China

  6. WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenes

    Aug 28, 2026Kishor Datta Gupta, Ahmed Rafi Hasan, Md. Mahfuzur Rahman +2Object DetectionFew-Shot Object Detection

    Department of Cyber Physical Systems, Clark Atlanta University, Atlanta, GA, USA · Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh

  7. Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR

    Aug 25, 2026Sheethal Bhat, Bogdan Georgescu, Awais Mansoor +5Object DetectionMedical Image Anomaly Detection

  8. Class Geometry as Supervision for Sample-Efficient Open-World Detection

    Aug 13, 2026Akash Rao, Zhou Chen, Revanth Reddy Palem +3Open-Vocabulary Object DetectionPrototype-Based Classification

    CSSE Department, Auburn University, Auburn, AL, 36849 · Department of Veterinary Pathobiology, Oklahoma State University, Stillwater, OK, 74078

  9. Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection

    Aug 5, 2026Zijian Zhuang, Yixiong Zou, Yuhua Li +1Synthetic Data AugmentationData Augmentation

    School of Computer Science and Technology, Huazhong University of Science and Technology, China

  10. Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection

    Aug 2, 2026Linhai Zhuo, Junxi Cai, Tianwen Qian +2Synthetic Data AugmentationFew-Shot Domain Adaptation

    Fuzhou University · East China Normal University · Xiamen University +1

  11. Rough Path Signature-Guided Geometry Augmentation for Few-Shot Industrial Surface Defect Detection

    Jul 14, 2026Jiaqi KuangFew-Shot Anomaly DetectionData Augmentation

    Oxford Suzhou Centre for Advanced Research, University of Oxford Suzhou, China

  12. Personalized Object Identification and Localization via In-Context Inference with Vision-Language Models

    Jul 1, 2026Kensuke Nakamura, Byung-Woo HongFew-Shot Object DetectionVision-Language Grounding

    Artificial Intelligence Department, Chung-Ang University, Seoul, 06974, Korea

  13. Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection

    Jun 22, 2026KunHo Heo, Seungjae Kim, Wongyu Lee +2Prototype-Based ClassificationFew-Shot Object Detection

    Kyung Hee University, Republic of Korea

  14. Proposal Refinement for Few-Shot Object Detection

    Jun 8, 2026Yuan Zeng, Bin Song, Jie Guo +1Class-Imbalanced LearningFew-Shot Object Detection

    State Key Laboratory of Integrated Services Networks, Xidian University, 710071, China

  15. GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection

    May 28, 2026Jiacong Liu, Shu Luo, Yikai Qin +3Synthetic Data AugmentationFew-Shot Domain Adaptation

    Huazhong University of Science and Technology

  16. Decoupled Prototype Matching with Vision Foundation Models for Few-Shot Industrial Object Detection

    Apr 29, 2026Hari Prasanth S. M., Nilusha Jayawickrama, Risto OjalaFew-Shot Object DetectionObject Detection

    Department of Energy and Mechanical Engineering, Aalto University, Espoo, 02150, Finland.

  17. Class-specific diffusion models improve military object detection in a low-data domain

    Apr 20, 2026Ella P. Fokkinga, Jan Erik van Woerden, Thijs A. Eker +4Synthetic Data AugmentationDiffusion Model Guidance

    TNO - Intelligent Imaging, Oude Waalsdorperweg 63, the Hague, the Netherlands

  18. The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results

    Apr 13, 2026Xingyu Qiu, Yuqian Fu, Jiawei Geng +71Few-Shot Object DetectionObject Detection

  19. Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments

    Apr 9, 2026Yun Zhu, Jianjun Qian, Jian Yang +23D Object DetectionFew-Shot Object Detection

    Nanjing University of Science and Technology · Nanjing University · Singapore University of Technology and Design

  20. A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps

    Mar 30, 2026Xuanlong Yu, Youyang Sha, Longfei Liu +2Few-Shot Object DetectionObject Detection

    Intellindust AI Lab · Suzhou Institute for Advanced Research, USTC

  21. DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection

    Mar 24, 2026Gautam Rajendrakumar Gare, Neehar Peri, Matvei Popov +3Large Vision-Language ModelsFew-Shot Object Detection

    Carnegie Mellon University · Roboflow

  22. Remedying Target-Domain Astigmatism for Cross-Domain Few-Shot Object Detection

    Mar 19, 2026Yongwei Jiang, Yixiong Zou, Yuhua Li +1Few-Shot Object DetectionObject Detection

    School of Computer Science and Technology, Huazhong University of Science and Technology

  23. Evaluating Few-Shot Pill Recognition Under Visual Domain Shift

    Mar 11, 2026W. I. Chu, G. Tarroni, L. LiFew-Shot Object DetectionObject Detection

    Department of Engineering, City St George’s, University of London, London, United Kingdom · Department of Computer Science, City St George’s, University of London, London, United Kingdom

  24. Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detection

    Feb 21, 2026Wanqi Wang, Jingcai Guo, Yuxiang Cai +1Few-Shot Object DetectionObject Detection

    University of Chinese Academy of Sciences · The Hong Kong Polytechnic University · Zhejiang University +1

  25. From Words to Wavelengths: VLMs for Few-Shot Multispectral Object Detection

    Dec 17, 2025Manuel Nkegoum, Minh-Tan Pham, Élisa Fromont +2VLM AdaptationMultispectral Object Detection

    Univ Bretagne Sud, IRISA, UMR 6074, Vannes, France · ATERMES, Montigny-le-Bretonneux, France · Univ Rennes, IRISA, UMR 6074, Rennes, France +1

  26. MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment

    Sep 17, 2025Elena Camuffo, Francesco Barbato, Mete Ozay +2Cross-Modal Knowledge DistillationEfficient Object Detection

    Samsung R&D Institute UK, United Kingdom · University of Padova, Italy

  27. AutoExpert: Automating 3D LiDAR Annotation from Expert-Crafted Guidelines

    Jun 3, 2025Yechi Ma, Wei Hua, Shu KongAutonomous Driving DatasetsLidar-Based 3D Object Detection

    Zhejiang University · University of Macau · IAIBS