Learning Deep Parsimonious Representations

Part of Advances in Neural Information Processing Systems 29 (NIPS 2016)

Bibtex »Metadata »Paper »Reviews »


Renjie Liao, Alex Schwing, Richard Zemel, Raquel Urtasun


<p>In this paper we aim at facilitating generalization for deep networks while supporting interpretability of the learned representations. Towards this goal, we propose a clustering based regularization that encourages parsimonious representations. Our k-means style objective is easy to optimize and flexible supporting various forms of clustering, including sample and spatial clustering as well as co-clustering. We demonstrate the effectiveness of our approach on the tasks of unsupervised learning, classification, fine grained categorization and zero-shot learning.</p>