Information Fusion: Scaling Subspace-Driven Approaches. (arXiv:2204.12035v1 [cs.LG])

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 …

arxiv fusion information scaling