OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features
Not on the map. Why?
Abstract (arXiv)
In this paper, we consider the task of one-shot object detection, which consists in detecting objects defined by a single demonstration. Differently from the standard object detection, the classes of objects used for training and testing do not overlap. We build the one-stage system that performs localization and recognition jointly. We use dense correlation matching of learned local features to find correspondences, a feed-forward geometric transformation model to align features and bilinear resampling of the correlation tensor to compute the detection score of the aligned features. All the components are differentiable, which allows end-to-end training. Experimental evaluation on several challenging domains (retail products, 3D objects, buildings and logos) shows that our method can detect unseen classes (e.g., toothpaste when trained on groceries) and outperforms several baselines by a significant margin. Our code is available online: https://github.com/aosokin/os2d .
Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Mar 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 11; 2023: 7; 2024: 5; 2025: 2; 2026: 5.
35 papers.
Sort:
By area:
- 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 303
- 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
- 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
- 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
- 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
- 2023Multi-Modal Classifiers for Open-Vocabulary Object Detectioncited by 53
- 2021Hallucination Improves Few-Shot Object Detectioncited by 50
- 2024Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentationcited by 17
- 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splattingcited by 14
- 2022Semantic-aligned Fusion Transformer for One-shot Object Detectioncited by 13
- 2022LocPoseNet: Robust Location Prior for Unseen Object Pose Estimationcited by 9
23 more
- 2022Mobile Robot Manipulation using Pure Object Detectioncited by 8
- 2023VoxDet: Voxel Learning for Novel Instance Detectioncited by 8
- 2021A Survey of Deep Learning for Low-Shot Object Detectioncited by 6
- 2024Object Detection using Oriented Window Learning Vi-sion Transformer: Roadway Assets Recognitioncited by 6
- 2025Solving Instance Detection from an Open-World Perspectivecited by 6
- 2023Towards Content-based Pixel Retrieval in Revisited Oxford and Pariscited by 5
- 2021CAT: Cross-Attention Transformer for One-Shot Object Detectioncited by 3
- 2022An Improved Deep Learning Approach For Product Recognition on Racks in Retail Storescited by 2
- 2023Low-shot Object Learning with Mutual Exclusivity Biascited by 2
- 2024Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Mangacited by 2
- 2022Novel 3D Scene Understanding Applications From Recurrence in a Single Imagecited by 1
- 2023VGTS: Visually Guided Text Spotting for Novel Categories in Historical Manuscriptscited by 1
- 2025Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimizationcited by 1
- 2022Automatic Bounding Box Annotation with Small Training Data Sets for Industrial Manufacturingcited by 0
- 2022One-Shot General Object Localizationcited by 0
- 2023Sketch-based Video Object Localizationcited by 0
- 2023GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detectioncited by 0
- 2024Accurate and Fast Pixel Retrieval with Spatial and Uncertainty Aware Hypergraph Diffusioncited by 0
- 2026From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenescited by 0
- 2026Reference-based Category Discovery: Unsupervised Object Detection with Category Awarenesscited by 0
- 2026UniRef-UAV: A Multimodal Benchmark for Universal Referring in UAV Imagerycited by 0
- 2026WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenescited by 0
- 2026Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perceptioncited by 0
- 2026Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perception8 Sep 2026
- 2026WALDO: One-Shot Exemplar-Conditioned Object Detection in Cluttered Scenes28 Aug 2026
- 2026UniRef-UAV: A Multimodal Benchmark for Universal Referring in UAV Imagery9 Jul 2026
- 2026Reference-based Category Discovery: Unsupervised Object Detection with Category Awareness6 May 2026
- 2026From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes3 Mar 2026
- 2025Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization10 Mar 2025
- 2025Solving Instance Detection from an Open-World Perspective1 Mar 2025
- 2024Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga8 Oct 2024
- 2024Accurate and Fast Pixel Retrieval with Spatial and Uncertainty Aware Hypergraph Diffusion17 Jun 2024
- 2024Object Detection using Oriented Window Learning Vi-sion Transformer: Roadway Assets Recognition15 Jun 2024
- 2024Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation28 May 2024
- 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting15 Mar 2024
23 more
- 2023GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detection27 Dec 2023
- 2023Low-shot Object Learning with Mutual Exclusivity Bias6 Dec 2023
- 2023Towards Content-based Pixel Retrieval in Revisited Oxford and Paris11 Sep 2023
- 2023Multi-Modal Classifiers for Open-Vocabulary Object Detection8 Jun 2023
- 2023VoxDet: Voxel Learning for Novel Instance Detection26 May 2023
- 2023VGTS: Visually Guided Text Spotting for Novel Categories in Historical Manuscripts3 Apr 2023
- 2023Sketch-based Video Object Localization2 Apr 2023
- 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare13 Dec 2022
- 2022LocPoseNet: Robust Location Prior for Unseen Object Pose Estimation29 Nov 2022
- 2022One-Shot General Object Localization24 Nov 2022
- 2022Novel 3D Scene Understanding Applications From Recurrence in a Single Image14 Oct 2022
- 2022Automatic Bounding Box Annotation with Small Training Data Sets for Industrial Manufacturing1 Jun 2022
- 2022Simple Open-Vocabulary Object Detection with Vision Transformers12 May 2022
- 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images22 Apr 2022
- 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Framework29 Mar 2022
- 2022Semantic-aligned Fusion Transformer for One-shot Object Detection17 Mar 2022
- 2022An Improved Deep Learning Approach For Product Recognition on Racks in Retail Stores26 Feb 2022
- 2022Mobile Robot Manipulation using Pure Object Detection28 Jan 2022
- 2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks17 Dec 2021
- 2021A Survey of Deep Learning for Low-Shot Object Detection6 Dec 2021
- 2021Hallucination Improves Few-Shot Object Detection4 May 2021
- 2021CAT: Cross-Attention Transformer for One-Shot Object Detection30 Apr 2021
- 2021Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment15 Apr 2021
- 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 303
- 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
- 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
- 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
- 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
- 2023Multi-Modal Classifiers for Open-Vocabulary Object Detectioncited by 53
- 2021Hallucination Improves Few-Shot Object Detectioncited by 50
- 2024Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentationcited by 17
- 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splattingcited by 14
- 2022Semantic-aligned Fusion Transformer for One-shot Object Detectioncited by 13
- 2022LocPoseNet: Robust Location Prior for Unseen Object Pose Estimationcited by 9
12 most cited of 34 All 34 (JSON)
- 2026Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perception8 Sep 2026
- 2026UniRef-UAV: A Multimodal Benchmark for Universal Referring in UAV Imagery9 Jul 2026
- 2026Reference-based Category Discovery: Unsupervised Object Detection with Category Awareness6 May 2026
- 2026From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes3 Mar 2026
- 2025Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization10 Mar 2025
- 2025Solving Instance Detection from an Open-World Perspective1 Mar 2025
- 2024Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga8 Oct 2024
- 2024Accurate and Fast Pixel Retrieval with Spatial and Uncertainty Aware Hypergraph Diffusion17 Jun 2024
- 2024Object Detection using Oriented Window Learning Vi-sion Transformer: Roadway Assets Recognition15 Jun 2024
- 2024Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation28 May 2024
- 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting15 Mar 2024
- 2023GRSDet: Learning to Generate Local Reverse Samples for Few-shot Object Detection27 Dec 2023
12 newest of 34 All 34 (JSON)