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 ...
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...
Y-Lan Boureau, Francis Bach, Yann LeCun, Jean Ponc...
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...
Several recently-proposed architectures for highperformance
object recognition are composed of two main
stages: a feature extraction stage that extracts locallyinvariant
feature...
Koray Kavukcuoglu, Marc'Aurelio Ranzato, Rob Fergu...