Collaborative Descriptors: Convolutional Maps for Preprocessing

Autor:	Kataoka, Hirokatsu, Abe, Kaori, Nakamura, Akio, Satoh, Yutaka
Rok vydání:	2017
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning
Druh dokumentu:	Working Paper
Popis:	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 % (multi-class object recognition) and +24.71 % (car detection) from grayscale input to convolutional maps. Although the framework is straight-forward, the concept should be inherited for an improved representation. Comment: CVPR 2017 Workshop Submission
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1705.03595 Zobrazit plný text záznamu View this record from Arxiv