Multi-Level Convolutional Channel Features for Content-Based Image Retrieval

被引：0

作者：

Hu, Kun ^{[1
]}

Dong, Yuan ^{[1
]}

Bai, Hongliang ^{[2
]}

机构：

[1] Beijing Univ Posts & Telecommun, Sch Informat & Commun Engn, Beijing, Peoples R China

[2] Beijing FaceAll Co Beijing, Beijing, Peoples R China

来源：

2016 30TH ANNIVERSARY OF VISUAL COMMUNICATION AND IMAGE PROCESSING (VCIP) | 2016年

关键词：

CBIR; Convolutional Neural Network; Deep learning; Multi-level pooling; PCA;

D O I：

暂无

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

An effective content-based image retrieval (CBIR) system depends on the discriminative feature which represents an image. In this work, we explore deep convolutional features for a CBIR system. We first show the effectiveness of deep convolutional channel features for a CBIR system. Then we introduce a Multi Level Pooling method (MLP) to obtain object-aware features from convolutional layers and finally the features extracted from different layers are incorporated to a short representation vector. Through multiple experiments, we show that our approach can achieve state-of-art results on several benchmark retrieval datasets.

引用

页数：4