...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Subsurface Sensing Technologies and Applications >Unsupervised Feature Learning with Single Layer ICANet for Face Recognition
【24h】

Unsupervised Feature Learning with Single Layer ICANet for Face Recognition

机译：使用单层ICANet进行人脸识别的无监督特征学习

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Compared to supervised learning, unsupervised learning allows systemsrnto learn consistent patterns from cheap and abundant unlabeled data, without thernneed for manual annotation. In this paper, we present a novel unsupervised featurernlearning method with single layer (SL) network based independent componentrnanalysis (ICA) filters called SL-ICANet, with the goal of achieving compact andrnrobust facial feature representation. Our contributions are twofold: (ⅰ) We developedrna single-layer convolutional network for unsupervised learning wherein the trainable kernels are replaced by ICA filters. (ⅱ) We extended our SL-ICANet to usernmulti-scale information for better feature learning. Extensive experiments on twornpopular face recognition benchmarks, namely, labeled faces in the wild and facialrnrecognition technology show that the proposed method might serve as a simple butrnhighly competitive baseline for face recognition.
机译：与有监督的学习相比，无监督的学习允许系统从便宜而丰富的未标记数据中学习一致的模式，而无需人工注释。在本文中，我们提出了一种新颖的无监督特征学习方法，即基于单层（SL）网络的独立成分分析（ICA）过滤器，称为SL-ICANet，目的是实现紧凑且鲁棒的面部特征表示。我们的贡献是双重的：（ⅰ）我们开发了用于无监督学习的单层卷积网络，其中可训练内核被ICA过滤器取代。 （ⅱ）我们将SL-ICANet扩展到了用户多尺度信息，以便更好地学习特征。在两个流行的人脸识别基准上进行了广泛的实验，即在野外和人脸识别技术中标记了人脸，表明该方法可以作为简单但竞争激烈的人脸识别基线。

著录项

  • 来源
    《Subsurface Sensing Technologies and Applications》 |2018年第1期|5.1-5.10|共10页
  • 作者

    Tianyu Geng; Yongqing Zhang; Ying Cai; Menglong Yang; Hailong Jing;

  • 作者单位

    College of Computer Science, Sichuan University, Chengdu, People’s Republic of China National Key Laboratory of Fundamental Science on Synthetic Vision, Chengdu, People’s Republic of China;

    School of Computer Science, Chengdu University of Information Technology, Chengdu, People’s Republic of China School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, People’s Republic of China;

    College of Information Engineering, Sichuan Agricultural University, Yaan 625014, People’s Republic of China;

    School of Aeronautics and Astronautics, Sichuan University, Chengdu, People’s Republic of China;

    National Key Laboratory of Fundamental Science on Synthetic Vision, Chengdu, People’s Republic of China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Unsupervised learning; Face recognition; LFW; FERET; ICANet;

    机译：无监督学习;人脸识别;LFW;FERET;网络;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号