4 search results - page 1 / 1 » Evaluation of Pooling Operations in Convolutional Architectu... |
ICANN
2010
Springer
13 years 5 months ago
2010
Springer
Abstract. A common practice to gain invariant features in object recognition models is to aggregate multiple low-level features over a small neighborhood. However, the differences ...
CVPR
2010
IEEE
14 years 1 months ago
2010
IEEE
Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of interme...
CVPR
2011
IEEE
12 years 11 months ago
2011
IEEE
Object recognition has made great strides recently. However, the best methods, such as those based on kernelSVMs are highly computationally intensive. The problem of how to accele...
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
Several recently-proposed architectures for highperformance
object recognition are composed of two main
stages: a feature extraction stage that extracts locallyinvariant
feature...