...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on visualization and computer graphics >VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification
【24h】

VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification

机译：VERAM：用于3D形状分类的视图增强的循环注意力模型

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Multi-view deep neural network is perhaps the most successful approach in 3D shape classification. However, the fusion of multi-view features based on max or average pooling lacks a view selection mechanism, limiting its application in, e.g., multi-view active object recognition by a robot. This paper presents VERAM, a view-enhanced recurrent attention model capable of actively selecting a sequence of views for highly accurate 3D shape classification. VERAM addresses an important issue commonly found in existing attention-based models, i.e., the unbalanced training of the subnetworks corresponding to next view estimation and shape classification. The classification subnetwork is easily overfitted while the view estimation one is usually poorly trained, leading to a suboptimal classification performance. This is surmounted by three essential view-enhancement strategies: 1) enhancing the information flow of gradient backpropagation for the view estimation subnetwork, 2) devising a highly informative reward function for the reinforcement training of view estimation and 3) formulating a novel loss function that explicitly circumvents view duplication. Taking grayscale image as input and AlexNet as CNN architecture, VERAM with 9 views achieves instance-level and class-level accuracy of 95.5 and 95.3 percent on ModelNet10, 93.7 and 92.1 percent on ModelNet40, both are the state-of-the-art performance under the same number of views.
机译：多视图深度神经网络可能是3D形状分类中最成功的方法。然而，基于最大或平均池的多视图特征的融合缺乏视图选择机制，从而限制了其在例如机器人的多视图活动对象识别中的应用。本文介绍了VERAM，这是一种视图增强的循环注意力模型，能够主动选择视图序列以进行高精度3D形状分类。 VERAM解决了在现有的基于注意力的模型中普遍存在的重要问题，即与下一视图估计和形状分类相对应的子网的不平衡训练。分类子网络很容易过度拟合，而视图估计通常训练不力，导致分类性能不佳。这是通过三种基本的视图增强策略来克服的：1）增强用于视图估计子网的梯度反向传播的信息流，2）设计用于增强视图估计训练的信息量大的奖励函数，以及3）提出一种新颖的损失函数明确规避视图重复。以灰度图像作为输入，以AlexNet作为CNN架构，具有9个视图的VERAM在ModelNet10上的实例级别和类级别的精度分别达到95.5％和95.3％，在ModelNet40上达到93.7％和92.1％，两者都是最新的性能在相同数量的视图下。

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