Collaborative Descriptors: Convolutional Maps for Preprocessing

05/10/2017

∙

by   Hirokatsu Kataoka, et al.

∙

0

∙

share

The paper presents a novel concept for collaborative descriptors between deeply learned and hand-crafted features. To achieve this concept, we apply convolutional maps for pre-processing, namely the convovlutional maps are used as input of hand-crafted features. We recorded an increase in the performance rate of +17.06 from grayscale input to convolutional maps. Although the framework is straight-forward, the concept should be inherited for an improved representation.