Deconvolutional networks

Building robust low and mid-level image representations, beyond edge primitives, is a long-standing goal in vision. Many existing feature detectors spatially pool edge information which destroys cues such as edge intersections, parallelism and symmetry. We present a learning framework where features...

Full description

Saved in:
Bibliographic Details
Published in2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 2528 - 2535
Main Authors Zeiler, M D, Krishnan, D, Taylor, G W, Fergus, R
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2010
Subjects
Computer architecture
Convolution
Decoding
Feature extraction
Filters
Image edge detection
Image representation
Image restoration
Object recognition
Robustness
Online AccessGet full text

Cover

More Information
Summary:Building robust low and mid-level image representations, beyond edge primitives, is a long-standing goal in vision. Many existing feature detectors spatially pool edge information which destroys cues such as edge intersections, parallelism and symmetry. We present a learning framework where features that capture these mid-level cues spontaneously emerge from image data. Our approach is based on the convolutional decomposition of images under a spar-sity constraint and is totally unsupervised. By building a hierarchy of such decompositions we can learn rich feature sets that are a robust image representation for both the analysis and synthesis of images.
ISBN:1424469848
9781424469840
ISSN:1063-6919
DOI:10.1109/CVPR.2010.5539957