Learning deep parsimonious representations

Renjie Liao, Alexander Gerhard Schwing, Richard S. Zemel, Raquel Urtasun

Research output: Contribution to journalConference article

Abstract

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, such as sample clustering, 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.

Original languageEnglish (US)
Pages (from-to)5092-5100
Number of pages9
JournalAdvances in Neural Information Processing Systems
StatePublished - Jan 1 2016
Event30th Annual Conference on Neural Information Processing Systems, NIPS 2016 - Barcelona, Spain
Duration: Dec 5 2016Dec 10 2016

Fingerprint

Unsupervised learning
Deep learning

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Learning deep parsimonious representations. / Liao, Renjie; Schwing, Alexander Gerhard; Zemel, Richard S.; Urtasun, Raquel.

In: Advances in Neural Information Processing Systems, 01.01.2016, p. 5092-5100.

Research output: Contribution to journalConference article

Liao, Renjie ; Schwing, Alexander Gerhard ; Zemel, Richard S. ; Urtasun, Raquel. / Learning deep parsimonious representations. In: Advances in Neural Information Processing Systems. 2016 ; pp. 5092-5100.
@article{4326c66cd5de48658e1a714da010a091,
title = "Learning deep parsimonious representations",
abstract = "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, such as sample clustering, 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.",
author = "Renjie Liao and Schwing, {Alexander Gerhard} and Zemel, {Richard S.} and Raquel Urtasun",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
pages = "5092--5100",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

TY - JOUR

T1 - Learning deep parsimonious representations

AU - Liao, Renjie

AU - Schwing, Alexander Gerhard

AU - Zemel, Richard S.

AU - Urtasun, Raquel

PY - 2016/1/1

Y1 - 2016/1/1

N2 - 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, such as sample clustering, 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.

AB - 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, such as sample clustering, 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.

UR - http://www.scopus.com/inward/record.url?scp=85018904825&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018904825&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85018904825

SP - 5092

EP - 5100

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -