Srinivas Kruthiventi - Academia.edu (original) (raw)

Srinivas Kruthiventi

Uploads

Papers by Srinivas Kruthiventi

Research paper thumbnail of SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition

Current state of the art object recognition architectures achieve impressive performance but are... more Current state of the art object recognition architectures achieve impressive
performance but are typically specialized for a single depictive style (e.g.
photos only, sketches only). In this paper, we present SwiDeN : our
Convolutional Neural Network (CNN) architecture which recognizes objects
regardless of how they are visually depicted (line drawing, realistic shaded
drawing, photograph etc.). In SwiDeN, we utilize a novel `deep' depictive
style-based switching mechanism which appropriately addresses the
depiction-specific and depiction-invariant aspects of the problem. We compare
SwiDeN with alternative architectures and prior work on a 50-category Photo-Art
dataset containing objects depicted in multiple styles. Experimental results
show that SwiDeN outperforms other approaches for the depiction-invariant
object recognition problem.

Research paper thumbnail of SwiDeN : Convolutional Neural Networks For Depiction Invariant Object Recognition

Current state of the art object recognition architectures achieve impressive performance but are... more Current state of the art object recognition architectures achieve impressive
performance but are typically specialized for a single depictive style (e.g.
photos only, sketches only). In this paper, we present SwiDeN : our
Convolutional Neural Network (CNN) architecture which recognizes objects
regardless of how they are visually depicted (line drawing, realistic shaded
drawing, photograph etc.). In SwiDeN, we utilize a novel `deep' depictive
style-based switching mechanism which appropriately addresses the
depiction-specific and depiction-invariant aspects of the problem. We compare
SwiDeN with alternative architectures and prior work on a 50-category Photo-Art
dataset containing objects depicted in multiple styles. Experimental results
show that SwiDeN outperforms other approaches for the depiction-invariant
object recognition problem.

Log In