新科学想法 › 学术文库 › 学术文献 › 浏览文献

UNSUPERVISED DEEP FEATURE EXTRACTION OF HYPERSPECTRAL IMAGES

mengyang1983 添加于 2014-11-25 21:33 | 1868 次阅读 | 0 个评论

作者
Romero A, Radeva P, Gatta C
摘要
We propose a meta-parameter free, off-the-shelf, simple and fast unsupervised feature learning algorithm, which exploits a new way of optimizing for sparsity. Experiments on STL-10 show that the method presents state-of-the-art performance and provides discriminative features that generalize well.
详细资料
- 关键词: cs.LG; cs.CV
- 文献种类: Manual Script
- 期卷页: 2014年
- 日期: 2014-2-24
- 发布方式: arXiv e-prints
- 备注:arXiv:1402.5766v1
学科领域信息系统 » 计算机科学
相关链接 URL