Collaborative Multi-View Denoising
Lei Zhang, Institute of Information Engin; Shupeng Wang, Iie; Xiao-Yu Zhang, IIE, CAS; Yong Wang, IIE,CAS; BinBin Li, Iie; Dinggang Shen, ; Shuiwang Ji*, Washington State University
In multi-view learning applications, like multimedia analysis and information retrieval, we often encounter the corrupted view problem in which the data are corrupted by two diﬀerent types of noises, i.e., the intra- and inter-view noises. The noises may aﬀect these applications that commonly acquire complementary representations from diﬀerent views. Therefore, how to denoise corrupted views from multi-view data is of great importance for applications that integrate and analyze representations from diﬀerent views. However, the heterogeneity among multi-view representations brings a signiﬁcant challenge on denoising corrupted views. To address this challenge, we propose a general framework to jointly denoise corrupted views in this paper. Speciﬁcally, aiming at capturing the semantic complementarity and distributional similarity among diﬀerent views, a novel Heterogeneous Linear Metric Learning (HLML) model with low-rank regularization, leave-one-out validation, and pseudo-metric constraints is proposed. Our method linearly maps multi-view data to a high-dimensional feature-homogeneous space that embeds the complementary information from diﬀerent views. Furthermore, to remove the intra- and inter-view noises, we present a new Multi-view Semi-supervised Collaborative Denoising (MSCD) method with elementary trans-formation constraints and gradient energy competition to establish the complementary relationship among the heterogeneous representations. Experimental results demonstrate that our proposed methods are eﬀective and eﬃcient.