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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition s. 2528 - 2535
Hlavní autoři: Zeiler, M D, Krishnan, D, Taylor, G W, Fergus, R
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2010
Témata:
Computer architecture
Convolution
Decoding
Feature extraction
Filters
Image edge detection
Image representation
Image restoration
Object recognition
Robustness
ISBN:1424469848, 9781424469840
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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
1063-6919
DOI:10.1109/CVPR.2010.5539957