Binary Similarity Few-Shot Object Detection With Modeling of Hard Negative Samples
文献类型：期刊论文
| 作者 | Lu, Yue1,3 ; Chen, Xingyu2; Wu, Zhengxing1,3; Tan, Min1,3; Yu, Junzhi2,3
|
| 刊名 | IEEE TRANSACTIONS ON MULTIMEDIA
 |
| 出版日期 | 2024 |
| 卷号 | 26页码:4805-4818 |
| 关键词 | Few-shot learning object detection computer vision deep learning |
| ISSN号 | 1520-9210 |
| DOI | 10.1109/TMM.2023.3326872 |
| 通讯作者 | Yu, Junzhi(junzhi.yu@ia.ac.cn) |
| 英文摘要 | For few-shot object detection, this work proposes a binary similarity detector (BSDet), which realizes a novel similarity-based multiple binary classification and enhances the feature margin between positive and hard negative samples. First, we revisit the classification paradigm, concluding that multiple binary classification paradigm is more suitable than multi-class classification paradigm for the few-shot task. Hence, we propose a binary similarity head (BSH) by posing the classification task as multiple binary similarity measurements rather than a multi-class prediction. Second, focusing on the hard negative samples, we propose a feature enhancement module (FEM). During training phase, the FEM can push the features of positive and hard negative samples far away from each other, and thus effectively suppresses false positives. Abundant experiments and visualizations indicate that our method achieves state-of-the-art performances on few-shot object detection tasks. |
| 资助项目 | National Natural Science Foundation of China |
| WOS研究方向 | Computer Science ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:001181498100008 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/56951]  |
| 专题 | 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.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Peking Univ, Coll Engn, Dept Adv Mfg & Robot, State Key Lab Turbulence & Complex Syst, Beijing 100871, Peoples R China 3.Chinese Acad Sci, Inst Automat, Lab Cognit & Decis Intelligence Complex Syst, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Lu, Yue,Chen, Xingyu,Wu, Zhengxing,et al. Binary Similarity Few-Shot Object Detection With Modeling of Hard Negative Samples[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2024,26:4805-4818. |
| APA | Lu, Yue,Chen, Xingyu,Wu, Zhengxing,Tan, Min,&Yu, Junzhi.(2024).Binary Similarity Few-Shot Object Detection With Modeling of Hard Negative Samples.IEEE TRANSACTIONS ON MULTIMEDIA,26,4805-4818. |
| MLA | Lu, Yue,et al."Binary Similarity Few-Shot Object Detection With Modeling of Hard Negative Samples".IEEE TRANSACTIONS ON MULTIMEDIA 26(2024):4805-4818. |
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。