Multi-View Autoencoder for Image Feature Learning with Structured Nonnegative Low Rank

Abstract

Multi-view feature learning has garnered much attention recently since many real-world data are comprised of different representations or views. As an important and challenging problem in multi-view feature learning, the key issue is how to explore complementary information and eliminate the inconsistency noise. Motivated by this observation, we propose to encode the multiple feature views to an underlying consensus representation. To enhance the robustness against the noise of disagreement among different feature views and exploit the consistency of the shared structure, we impose the nuclear norm constraint on the consensus representation and enforce the encoded representation to be nonnegative low rank structured. The superior experimental results on three image benchmarks show the effectiveness of our method.