Consensus Regularized Multi-View Outlier Detection

Abstract

Identifying different types of data outliers with abnormal behaviors in multi-view data setting is challenging due to the complicated data distributions across different views. Conventional approaches achieve this by learning a new latent feature representation with the pairwise constraint on different view data. In this paper, we argue that the existing methods are expensive in generalizing their models from two-view data to three-view (or more) data, in terms of the number of introduced variables and detection performance. To address this, we propose a novel multi-view outlier detection method with consensus regularization on the latent representations. Specifically, we explicitly characterize each kind of outliers by the intrinsic cluster assignment labels and sample-specific errors. Moreover, we make a thorough discussion about the proposed consensus-regularization and the pairwise-regularization. Correspondingly, an optimization solution based on augmented Lagrangian multiplier method is proposed and derived in details. In the experiments, we evaluate our method on five well-known machine learning data sets with different outlier settings. Further, to show its effectiveness in real-world computer vision scenario, we tailor our proposed model to saliency detection and face reconstruction applications. The extensive results of both standard multi-view outlier detection task and the extended computer vision tasks demonstrate the effectiveness of our proposed method.

Regularized deep learning for fashion and social media data analysis

“…Thus, they failed to consider the correlation between different kinds of features, i.e., consensus [65,66].…”

Robust unsupervised subspace learning for visual representation

“…As the real-world data are always captured from multiple sources or represented by several distinct feature sets [35,36,37,38,39,40], multi-view clustering is intensively studied recently by leveraging the heterogeneous data to achieve the same goal [36,38,41,42].…”

“…face image clustering [1,3] and motion/video segmentation [2,70,71], outlier detection [72] and many others [73,40]. Approximately, those data are lying in a set of subspaces, e.g.…”

“…label vector) andỸ is the ground truth. The ACC is defined as: 11) where N is the total number of samples, (x, y) is the delta function that equals one if x = y and equal zero otherwise. map(Y i ) function is the permutation mapping function that map each cluster label Y i to the equivalent label from the data corpus.…”

“…. From (b) to (e), they are the face reconstruction and their corresponding error images by LR [10], MLRA [9], DMOD [11] and the proposed method, respectively. .…”