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.
翻译:在这项工作中,我们试图利用多模式数据的深层结构,利用革命神经网络(CNN)的形式主义来强有力地利用信息分组子空间分布。在推出构成每个数据模式的一组子空间并学习相应的编码器后,对生成的固有信息进行优化整合,以得出不同类别的特征描述。这个方法被称为深多模式软体集团子空间集群(DROGSure ), 与独立开发的最新方法“深多模式子空间集群(DMCC) ” ( DMCC) 进行比较。 对不同多式联运数据集的实验表明,我们的方法具有竞争力,在出现噪音时更加有力。