Augmenting supervised neural networks with unsupervised objectives for large-scale image classification

Yuting Zhang, Kibok Lee, Honglak Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

32 Citations (Scopus)

Abstract

Unsupervised learning and supervised learning are key research topics in deep learning. However, as high-capacity supervised neural networks trained with a large amount of labels have achieved remarkable success in many computer vision tasks, the availability of large-scale labeled images reduced the significance of unsupervised learning. Inspired by the recent trend toward revisiting the importance of unsupervised learning, we investigate joint supervised and unsupervised learning in a large-scale setting by augmenting existing neural networks with decoding pathways for reconstruction. First, we demonstrate that the intermediate activations of pretrained large-scale classification networks preserve almost all the information of input images except a portion of local spatial details. Then, by end-to-end training of the entire augmented architecture with the reconstructive objective, we show improvement of the network performance for supervised tasks. We evaluate several variants of autoencoders, including the recently proposed "what-where" autoencoder that uses the encoder pooling switches, to study the importance of the architecture design. Taking the 16-layer VGGNet trained under the ImageNet ILSVRC 2012 protocol as a strong baseline for image classification, our methods improve the validation-set accuracy by a noticeable margin.

Original languageEnglish
Title of host publication33rd International Conference on Machine Learning, ICML 2016
EditorsMaria Florina Balcan, Kilian Q. Weinberger
PublisherInternational Machine Learning Society (IMLS)
Pages939-957
Number of pages19
ISBN (Electronic)9781510829008
Publication statusPublished - 2016
Event33rd International Conference on Machine Learning, ICML 2016 - New York City, United States
Duration: 2016 Jun 192016 Jun 24

Publication series

Name33rd International Conference on Machine Learning, ICML 2016
Volume2

Conference

Conference33rd International Conference on Machine Learning, ICML 2016
Country/TerritoryUnited States
CityNew York City
Period16/6/1916/6/24

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Augmenting supervised neural networks with unsupervised objectives for large-scale image classification'. Together they form a unique fingerprint.

Cite this