Decoupled Metric Network for Single-Stage Few-Shot Object Detection
文献类型：期刊论文
| 作者 | Lu, Yue3,4 ; Chen, Xingyu2; Wu, Zhengxing3,4; Yu, Junzhi1,4
|
| 刊名 | IEEE TRANSACTIONS ON CYBERNETICS
 |
| 出版日期 | 2022-02-24 |
| 页码 | 12 |
| 关键词 | Object detection Feature extraction Training Head Task analysis Shape Measurement Computer vision deep learning few-shot learning object detection |
| ISSN号 | 2168-2267 |
| DOI | 10.1109/TCYB.2022.3149825 |
| 通讯作者 | Yu, Junzhi(junzhi.yu@ia.ac.cn) |
| 英文摘要 | Within the last few years, great efforts have been made to study few-shot learning. Although general object detection is advancing at a rapid pace, few-shot detection remains a very challenging problem. In this work, we propose a novel decoupled metric network (DMNet) for single-stage few-shot object detection. We design a decoupled representation transformation (DRT) and an image-level distance metric learning (IDML) to solve the few-shot detection problem. The DRT can eliminate the adverse effect of handcrafted prior knowledge by predicting objectness and anchor shape. Meanwhile, to alleviate the problem of representation disagreement between classification and location (i.e., translational invariance versus translational variance), the DRT adopts a decoupled manner to generate adaptive representations so that the model is easier to learn from only a few training data. As for a few-shot classification in the detection task, we design an IDML tailored to enhance the generalization ability. This module can perform metric learning for the whole visual feature, so it can be more efficient than traditional DML due to the merit of parallel inference for multiobjects. Based on the DRT and IDML, our DMNet efficiently realizes a novel paradigm for few-shot detection, called single-stage metric detection. Experiments are conducted on the PASCAL VOC dataset and the MS COCO dataset. As a result, our method achieves state-of-the-art performance in few-shot object detection. The codes are available at https://github.com/yrqs/DMNet. |
| 资助项目 | National Key Research and Development Program of China[2019YFB1310300] ; National Natural Science Foundation of China[62022090] |
| WOS研究方向 | Automation & Control Systems ; Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000764856200001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/47966]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队 复杂系统管理与控制国家重点实验室_水下机器人 |
| 通讯作者 | Yu, Junzhi |
| 作者单位 | 1.Peking Univ, Coll Engn, BIC ESAT, Dept Adv Mfg & Robot,State Key Lab Turbulence & C, Beijing 100871, Peoples R China 2.Kuaishou Technol, Ytech, Beijing 100085, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Lu, Yue,Chen, Xingyu,Wu, Zhengxing,et al. Decoupled Metric Network for Single-Stage Few-Shot Object Detection[J]. IEEE TRANSACTIONS ON CYBERNETICS,2022:12. |
| APA | Lu, Yue,Chen, Xingyu,Wu, Zhengxing,&Yu, Junzhi.(2022).Decoupled Metric Network for Single-Stage Few-Shot Object Detection.IEEE TRANSACTIONS ON CYBERNETICS,12. |
| MLA | Lu, Yue,et al."Decoupled Metric Network for Single-Stage Few-Shot Object Detection".IEEE TRANSACTIONS ON CYBERNETICS (2022):12. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。