论文标题
信息融合：扩展子空间驱动的方法
Information Fusion: Scaling Subspace-Driven Approaches
论文作者
论文摘要
在这项工作中，我们试图利用多模式数据的深层结构，以使用卷积神经网络（CNN）形式主义稳健地利用信息的组子空间分布。在展开构成每种数据模式并学习相应编码器的子空间集合集合之后，进行了对生成的固有信息的优化集成，以产生各种类别的表征。被称为深度模式鲁棒组的子空间聚类（Drogsure），该方法与名为Deep Multimodal子空间聚类（DMSC）的独立开发的最新方法进行了比较。在不同的多模式数据集上的实验表明，在存在噪声的情况下，我们的方法具有竞争力，更健壮。
In this work, we seek to exploit the deep structure of multi-modal data to robustly exploit the group subspace distribution of the information using the Convolutional Neural Network (CNN) formalism. Upon unfolding the set of subspaces constituting each data modality, and learning their corresponding encoders, an optimized integration of the generated inherent information is carried out to yield a characterization of various classes. Referred to as deep Multimodal Robust Group Subspace Clustering (DRoGSuRe), this approach is compared against the independently developed state-of-the-art approach named Deep Multimodal Subspace Clustering (DMSC). Experiments on different multimodal datasets show that our approach is competitive and more robust in the presence of noise.
