跳至主導覽
跳至搜尋
跳過主要內容
國立陽明交通大學研發優勢分析平台 首頁
English
中文
首頁
人員
單位
研究成果
計畫
獎項
活動
貴重儀器
影響
按專業知識、姓名或所屬機構搜尋
FedDAD: Federated Domain Adaptation for Object Detection
Peggy Joy Lu
*
, Chia Yung Jui, Jen Hui Chuang
*
此作品的通信作者
資訊科學與工程研究所
資訊工程學系
研究成果
:
Article
›
同行評審
2
引文 斯高帕斯(Scopus)
總覽
指紋
指紋
深入研究「FedDAD: Federated Domain Adaptation for Object Detection」主題。共同形成了獨特的指紋。
排序方式
重量
按字母排序
Keyphrases
Domain Adaptive
100%
Adaptive Detector
100%
Federated Learning
100%
Domain Adaptive Object Detection
100%
Target Domain
66%
User Privacy
66%
Popular
33%
Learning Algorithm
33%
Object Detection
33%
Multiple Clients
33%
Source-free
33%
Data Confidentiality
33%
New Targets
33%
Object Class
33%
Learning Architecture
33%
Source Domain
33%
User Data
33%
Specific Object
33%
Detection Problem
33%
Real Objects
33%
Object Detection Algorithm
33%
Aggregated Model
33%
Annotated Images
33%
Level Alignment
33%
Domain Shift
33%
Cross-domain Adaptation
33%
Instance-level
33%
KAIST
33%
FedAvg
33%
Adaptive Federated Learning
33%
Dynamic Attention
33%
Adaptive Challenges
33%
Scene Variation
33%
Computer Science
Object Detection
100%
Domain Adaptation
100%
Federated Learning
100%
User Privacy
50%
Experimental Result
25%
Learning Algorithm
25%
Multiple Client
25%
Data Confidentiality
25%
User Data
25%
Instance Level
25%
Aggregate Model
25%