.png){kind=icon}
返回
Unsupervised feature learning with C-SVDDNet
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2016.06.001.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper we present a novel unsupervised feature learning network named C-SVDDNet, a single-layer K-means-based network towards compact and robust feature representation. Our contributions are three folds: (1) we introduce C-SVDD encoding, a generalization of the K-means local encoding that adapts to the distribution information and improves the robustness against outliers; (2) we propose a method that effectively embeds the spatial information of 2D data into the final representation based on a modified SIFT descriptor; and (3) we extend our C-SVDDNet to exploit multi-scale information for better feature learning. Extensive experiments on several popular object recognition benchmarks, such as STL-10, MINST, Holiday and Copydays shows that the proposed method yields comparable or better performance than that of the previous state-of-the-art unsupervised feature learning methods. (C) 2016 Elsevier Ltd. All rights reserved.
Keyword:
Unsupervised feature learning
K-means
Support Vector Data Description (SVDD)
Centering SVDD (C-SVDD)
C-SVDDNet
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
暂无机构信息
引用论文
分享收藏Nonlinearly Activated Neural Network for Solving Time-Varying Complex Sylvester Equation求解时变复Sylvester方程的非线性激活神经网络
PREAI
分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Artefactual Nanoparticle Activation of the Inflammasome Platform:
in Vitro
Evidence with a Nano-Formed Calcium PhosphateNanomedicineOAAI
NanomedicineIF0
OAAI分享收藏
分享收藏
查看更多内容