首页> 外文期刊>Multimedia Tools and Applications >Off-the-shelf CNN features for 3D object retrieval
【24h】

Off-the-shelf CNN features for 3D object retrieval

机译:用于3D对象检索的现成CNN功能

获取原文
获取原文并翻译 | 示例
           

摘要

Effective feature representation is crucial to view-based 3D object retrieval (V3OR). Most previous works employed hand-crafted features to represent the views of each object. Although deep learning based methods has shown its excellent performance in many vision tasks, it is hard to get excellent performance for unsupervised 3D object retrieval. In this paper, we propose to combine the off-the-shelf deep model and graph model to retrieve unseen objects. By employing the powerful deep classification models which are trained from millions of images, we obtain significant improvements compared with state of the art methods. We validate the effectiveness of the ready CNN from other domains that can greatly facilitate the representative ability of objects' views. In addition, we analyze the representative abilities of different fully connected layers for V3OR, and propose to employ multigraph learning to fuse the deep features of different layers. The autoencoder is then explored to improve the retrieval speed to a large extent. Experiments on two popular datasets are carried out to demonstrate the effectiveness of the proposed method.
机译:有效的特征表示对于基于视图的3D对象检索(V3OR)至关重要。以前的大多数作品都采用手工制作的特征来表示每个对象的视图。尽管基于深度学习的方法已经在许多视觉任务中显示出了出色的性能,但是很难在无人监督的3D对象检索中获得出色的性能。在本文中,我们建议将现成的深度模型和图模型结合起来以检索看不见的对象。通过使用功能强大的深度分类模型,该模型可以从数百万个图像中训练出来,与最先进的方法相比,我们获得了显着的改进。我们验证了来自其他领域的现成CNN的有效性,该有效性可以极大地促进对象视图的代表性。此外,我们分析了V3OR的不同完全连接层的代表能力,并建议采用多图学习融合不同层的深层特征。然后探索自动编码器以在很大程度上提高检索速度。对两个流行的数据集进行了实验,以证明该方法的有效性。

著录项

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