Detect an Object At Once without Fine-tuning
Not on the map. Why?
Abstract (arXiv)
When presented with one or a few photos of a previously unseen object, humans can instantly recognize it in different scenes. Although the human brain mechanism behind this phenomenon is still not fully understood, this work introduces a novel technical realization of this task. It consists of two phases: (1) generating a Similarity Density Map (SDM) by convolving the scene image with the given object image patch(es) so that the highlight areas in the SDM indicate the possible locations; (2) obtaining the object occupied areas in the scene through a Region Alignment Network (RAN). The RAN is constructed on a backbone of Deep Siamese Network (DSN), and different from the traditional DSNs, it aims to obtain the object accurate regions by regressing the location and area differences between the ground truths and the predicted ones indicated by the highlight areas in SDM. By pre-learning from labels annotated in traditional datasets, the SDM-RAN can detect previously unknown objects without fine-tuning. Experiments were conducted on the MS COCO, PASCAL VOC datasets. The results indicate that the proposed method outperforms state-of-the-art methods on the same task.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 35 references that are in the map. First posted on arXiv 4 Nov 2024.
Builds on
23 of 35 references.
References · 23
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2020Meta-Learning in Neural Networks: A Surveycited by 944
- 2016Fully-Convolutional Siamese Networks for Object Trackingcited by 566
- 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
- 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
- 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
- 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
11 more
- 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
- 2021Learning To Count Everythingcited by 149
- 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
- 2020Multi-Scale Positive Sample Refinement for Few-Shot Object Detectioncited by 116
- 2021Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detectioncited by 79
- 2021Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networkscited by 55
- 2017Few-Shot Learning Through an Information Retrieval Lenscited by 51
- 2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
- 2023Few-Shot Object Detection via Variational Feature Aggregationcited by 22
- 2023DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detectioncited by 21
- 2021AirDet: Few-Shot Detection without Fine-tuning for Autonomous Explorationcited by 12
Built on by
Citing papers per year: 2025: 1.
1 paper.