您好，欢迎访问上海市农业科学院 机构知识库！
上海市农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Transductive Transfer Learning to Specialize a Generic Classifier Towards a Specific Scene

文献类型： 会议论文

第一作者： Houda Maamatou

作者： Houda Maamatou 1 ; Thierry Chateau 1 ; Sami Gazzah 2 ; Yann Goyat 3 ; Najoua Essoukri Ben Amara 2 ;

作者机构： 1.Institut Pascal, Blaise Pascal University

2.SAGE ENISo, University of Sousse

3.Logiroad

关键词： Transductive Transfer Learning;Specialization;Generic Classifier;Pedestrian Detection;Sequential Monte Carlo Filter (SMC)

会议名称： International Conference on Computer Vision Theory and Applications

主办单位：

页码： 388-399

摘要： In this paper, we tackle the problem of domain adaptation to perform object-classification and detection tasks in video surveillance starting by a generic trained detector. Precisely, we put forward a new transductive transfer learning framework based on a sequential Monte Carlo filter to specialize a generic classifier towards a specific scene. The proposed algorithm approximates iteratively the target distribution as a set of samples (selected from both source and target domains) which feed the learning step of a specialized classifier. The output classifier is applied to pedestrian detection into a traffic scene. We have demonstrated by many experiments, on the CUHK Square Dataset and the MIT Traffic Dataset, that the performance of the specialized classifier outperforms the generic classifier and that the suggested algorithm presents encouraging results.

分类号： TP391.41-53

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：上海市农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台