CASIA OpenIR  > 智能感知与计算
Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation
Jian Liang1,2; Ran He1,2,3; Zhenan Sun1,2,3; Tieniu Tan1,2,3
2019
会议名称IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
会议日期2019
会议地点USA
摘要

    Conventional domain adaptation methods usually resort to deep neural networks or subspace learning to find invariant representations across domains.
    However, most deep learning methods highly rely on large-size source domains and are computationally expensive to train, while subspace learning methods always have a quadratic time complexity that suffers from the large domain size. 
    This paper provides a simple and efficient solution, which could be regarded as a well-performing baseline for domain adaptation tasks.
    
    Our method is built upon the nearest centroid classifier, seeking a subspace where the centroids in the target domain are moderately shifted from those in the source domain.
    Specifically, we design a unified objective without accessing the source domain data and adopt an alternating minimization scheme to iteratively discover the pseudo target labels, invariant subspace, and target centroids.
    Besides its privacy-preserving property (distant supervision), the algorithm is provably convergent and has a promising linear time complexity.       
    In addition, the proposed method can be readily extended to multi-source setting and domain generalization, and it remarkably enhances popular deep adaptation methods by borrowing the learned transferable features.
    Extensive experiments on several benchmarks including object, digit, and face recognition datasets validate that our methods yield state-of-the-art results in various domain adaptation tasks.

关键词Domain Adaptation
收录类别EI
语种英语
七大方向——子方向分类知识表示与推理
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/23805
专题智能感知与计算
作者单位1.CRIPAC \& NLPR, Institute of Automation, Chinese Academy of Sciences (CAS)
2.CAS Center for Excellence in Brain Science and Intelligence Technology
3.University of Chinese Academy of Sciences
第一作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Jian Liang,Ran He,Zhenan Sun,et al. Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation[C],2019.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
1847.pdf(607KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Jian Liang]的文章
[Ran He]的文章
[Zhenan Sun]的文章
百度学术
百度学术中相似的文章
[Jian Liang]的文章
[Ran He]的文章
[Zhenan Sun]的文章
必应学术
必应学术中相似的文章
[Jian Liang]的文章
[Ran He]的文章
[Zhenan Sun]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 1847.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

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。