We propose probabilistic latent variable models for multi-view anomaly detection, which is the task of finding instances that have inconsistent views given multi-view data. With the proposed model, all views of a non-anomalous instance are assumed to be generated from a single latent vector. On the other hand, an anomalous instance is assumed to have multiple latent vectors, and its different views are generated from different latent vectors. By inferring the number of latent vectors used for each instance with Dirichlet process priors, we obtain multi-view anomaly scores. The proposed model can be seen as a robust extension of probabilistic canonical correlation analysis for noisy multi-view data. We present Bayesian inference procedures for the proposed model based on a stochastic EM algorithm. The effectiveness of the proposed model is demonstrated in terms of performance when detecting multi-view anomalies.

The agent pulls an arm and observes the corresponding return provided by the environment.

If we consider for example the image pictured in Figure 1 on the left, we can easily describe its content by'what' we see - the building, sky and a flag.

Tothisendweproposeaflow-based image-to-image model, called FlowU-Net with Squeeze modules (FUNS), that allows us to disentangle the features while retaining the ability to generate highquality diverse images from condition images.

Watermarking images is critical for tracking image provenance and proving ownership.

Neural Information Processing Systems http://nips.cc/

Success stories of deep reinforcement learning (RL) from high dimensional inputs such as pixels or large spatial layouts include achieving superhuman performance on Atari games [30, 37, 1], grandmaster levelinStarcraft II[50]andgrasping adiverse setofobjects with impressivesuccess rates and generalization with robots in the real world [21].