Adaptive deconvolutional networks for mid and high level feature learning

Matthew D. Zeiler, Graham W. Taylor, Rob Fergus

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

Abstract

We present a hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling. When trained on natural images, the layers of our model capture image information in a variety of forms: low-level edges, mid-level edge junctions, high-level object parts and complete objects. To build our model we rely on a novel inference scheme that ensures each layer reconstructs the input, rather than just the output of the layer directly beneath, as is common with existing hierarchical approaches. This makes it possible to learn multiple layers of representation and we show models with 4 layers, trained on images from the Caltech-101 and 256 datasets. When combined with a standard classifier, features extracted from these models outperform SIFT, as well as representations from other feature learning methods.

Original languageEnglish (US)
Title of host publication2011 International Conference on Computer Vision, ICCV 2011
Pages2018-2025
Number of pages8
DOIs
StatePublished - 2011
Event2011 IEEE International Conference on Computer Vision, ICCV 2011 - Barcelona, Spain
Duration: Nov 6 2011Nov 13 2011

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Other

Other2011 IEEE International Conference on Computer Vision, ICCV 2011
CountrySpain
CityBarcelona
Period11/6/1111/13/11

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Adaptive deconvolutional networks for mid and high level feature learning'. Together they form a unique fingerprint.

Cite this