SwiDeN: Convolutional Neural Networks For Depiction Invariant Object Recognition
Published in
ACM Multimedia(2016)External Links:
TL
TL;DR
In SwiDeN, a novel `deep' depictive style-based switching mechanism is utilized which appropriately addresses the depiction-specific and depiction-invariant aspects of the problem.
Abstract
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.
References20 items
1
Atoms of recognition in human and computer vision
2
Deep Residual Learning for Image Recognition
3
Beyond Photo-Domain Object Recognition: Benchmarks for the Cross-Depiction Problem
4
The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs
5