中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 机器人应用与理论组
Incremental few-shot object detection via knowledge transfer

文献类型：期刊论文

作者Feng, Hangtao2,3; Zhang, Lu2,3; Yang, Xu2,3; Liu, Zhiyong1,2,3
刊名PATTERN RECOGNITION LETTERS
出版日期2022-04-01
卷号156页码:67-73
关键词Machine learning Convolutional neural networks Transfer learning Incremental few-shot object detection
ISSN号0167-8655
DOI10.1016/j.patrec.2022.01.024
通讯作者Liu, Zhiyong(zhiyong.liu@ia.ac.cn)
英文摘要As a challenging problem in machine learning, incremental few-shot object detection (iFSD) [1] aims to incrementally detect novel classes with few examples, while keeping the previous knowledge without revisiting base classes. Here, we propose two models based on the observation that when new memories come, new connections will be created between memory cells in the brain [2] . The first one, which is called the multi-class head (MCH) model, simulates how humans add new memory-connections that every time novel classes come, a classification branch is added to predict novel classification. And the second model, called the bi-path multi-class head (BPMCH) model, adds a new backbone, which is initialized with the weight of the base class backbone, to transfer more knowledge of the base class to the novel class. Considering accuracy and speed, we choose the Fully Convolutional One-Stage Object Detection (FCOS) [3] + Adaptive Training Sample Selection (ATSS) [4] detector as our baseline. Our models are first trained on the base classes with abundant examples and then finetuned on novel classes with few examples, which not only maintain the knowledge learned from the base class but also transfer the knowledge to the novel class. Extensive experiments show that our models outperform the state-of-theart model ONCE [1] on the COCO [5] and PASCAL VOC [6] by a large margin. (c) 2022 Elsevier B.V. All rights reserved.
资助项目National Key Research and Development Plan of China[2020AAA0108902] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32050100] ; NSFC[61627808] ; Dongguan Core Technology Research Frontier Project, China[2019622101001]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000789226600010
出版者ELSEVIER
资助机构National Key Research and Development Plan of China ; Strategic Priority Research Program of Chinese Academy of Science ; NSFC ; Dongguan Core Technology Research Frontier Project, China
源URL[http://ir.ia.ac.cn/handle/173211/49377]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组
多模态人工智能系统全国重点实验室
通讯作者Liu, Zhiyong
作者单位1.Chinese Acad Sci China, Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Feng, Hangtao,Zhang, Lu,Yang, Xu,et al. Incremental few-shot object detection via knowledge transfer[J]. PATTERN RECOGNITION LETTERS,2022,156:67-73.
APA Feng, Hangtao,Zhang, Lu,Yang, Xu,&Liu, Zhiyong.(2022).Incremental few-shot object detection via knowledge transfer.PATTERN RECOGNITION LETTERS,156,67-73.
MLA Feng, Hangtao,et al."Incremental few-shot object detection via knowledge transfer".PATTERN RECOGNITION LETTERS 156(2022):67-73.

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。