Abstract
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 Networks (CNNs) 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.
Reference42 articles.
1. Elhamifar E, Vidal R. Sparse subspace clustering: Algorithm, theory, and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2013;35:2765-2781
2. Favaro P, Vidal R, Ravichandran A. A closed form solution to robust subspace estimation and clustering. In: CVPR 2011. Colorado springs, Colorado, USA: IEEE; 2011. pp. 1801-1807
3. Li CG, Vidal R. Structured sparse subspace clustering: A unified optimization framework. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE; 2015. pp. 277-286
4. Bian X, Panahi A, Krim H. Bi-sparsity pursuit: A paradigm for robust subspace recovery. Signal Processing. 2018;152:148-159
5. Yang AY, Rao SR, Ma Y. Robust statistical estimation and segmentation of multiple subspaces. In: 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW’06). New York, NY, USA: IEEE; 2006. p. 99