Reducing redundancy in the bottleneck representation of autoencoders

Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

Abstract: Highlights•We propose a scheme to avoid redundant features in the bottleneck representation of autoencoders.•We explicitly penalize the pair-wise correlations between the features and learn a diverse compressed embedding.•The proposed penalty acts as an unsupervised regularizer and can be integrated into any autoencoder model.